Hugging Face's logo

fortminors
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
fortminors commited on
Commit
2df4191
•
1 Parent(s): 957a71f

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1724273840.96f39a858e07 +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000650_2662400_reward_5.059.pth +3 -0
  5. checkpoint_p0/checkpoint_000000935_3829760.pth +3 -0
  6. checkpoint_p0/checkpoint_000000978_4005888.pth +3 -0
  7. config.json +142 -0
  8. replay.mp4 +3 -0
  9. sf_log.txt +969 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
.summary/0/events.out.tfevents.1724273840.96f39a858e07 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d682fc374fb81a4547b21dfd2c17495f6bd8f61ca2620686d50ec355769ed21
3
+ size 928065
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sample-factory
3
+ tags:
4
+ - deep-reinforcement-learning
5
+ - reinforcement-learning
6
+ - sample-factory
7
+ model-index:
8
+ - name: APPO
9
+ results:
10
+ - task:
11
+ type: reinforcement-learning
12
+ name: reinforcement-learning
13
+ dataset:
14
+ name: doom_health_gathering_supreme
15
+ type: doom_health_gathering_supreme
16
+ metrics:
17
+ - type: mean_reward
18
+ value: 4.06 +/- 0.70
19
+ name: mean_reward
20
+ verified: false
21
+ ---
22
+
23
+ A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
24
+
25
+ This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
26
+ Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
27
+
28
+
29
+ ## Downloading the model
30
+
31
+ After installing Sample-Factory, download the model with:
32
+ ```
33
+ python -m sample_factory.huggingface.load_from_hub -r fortminors/rl_course_vizdoom_health_gathering_supreme
34
+ ```
35
+
36
+
37
+ ## Using the model
38
+
39
+ To run the model after download, use the `enjoy` script corresponding to this environment:
40
+ ```
41
+ python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
42
+ ```
43
+
44
+
45
+ You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
46
+ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
47
+
48
+ ## Training with this model
49
+
50
+ To continue training with this model, use the `train` script corresponding to this environment:
51
+ ```
52
+ python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
53
+ ```
54
+
55
+ Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
56
+
checkpoint_p0/best_000000650_2662400_reward_5.059.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6be9e19fe312d555dbafeddc9b2c74d8440d34048013087adda754bbd5bb4b8
3
+ size 34929051
checkpoint_p0/checkpoint_000000935_3829760.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32e472fd9c7ba4eff33900bf5ad3d3ba072ad8a4af2b50794da98d76a743559
3
+ size 34929477
checkpoint_p0/checkpoint_000000978_4005888.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff28ae3749dc198168ae3c123f46565fce2a02012e9986019054d84c17f00e6f
3
+ size 34929477
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "help": false,
3
+ "algo": "APPO",
4
+ "env": "doom_health_gathering_supreme",
5
+ "experiment": "default_experiment",
6
+ "train_dir": "/content/train_dir",
7
+ "restart_behavior": "resume",
8
+ "device": "gpu",
9
+ "seed": null,
10
+ "num_policies": 1,
11
+ "async_rl": true,
12
+ "serial_mode": false,
13
+ "batched_sampling": false,
14
+ "num_batches_to_accumulate": 2,
15
+ "worker_num_splits": 2,
16
+ "policy_workers_per_policy": 1,
17
+ "max_policy_lag": 1000,
18
+ "num_workers": 8,
19
+ "num_envs_per_worker": 4,
20
+ "batch_size": 1024,
21
+ "num_batches_per_epoch": 1,
22
+ "num_epochs": 1,
23
+ "rollout": 32,
24
+ "recurrence": 32,
25
+ "shuffle_minibatches": false,
26
+ "gamma": 0.99,
27
+ "reward_scale": 1.0,
28
+ "reward_clip": 1000.0,
29
+ "value_bootstrap": false,
30
+ "normalize_returns": true,
31
+ "exploration_loss_coeff": 0.001,
32
+ "value_loss_coeff": 0.5,
33
+ "kl_loss_coeff": 0.0,
34
+ "exploration_loss": "symmetric_kl",
35
+ "gae_lambda": 0.95,
36
+ "ppo_clip_ratio": 0.1,
37
+ "ppo_clip_value": 0.2,
38
+ "with_vtrace": false,
39
+ "vtrace_rho": 1.0,
40
+ "vtrace_c": 1.0,
41
+ "optimizer": "adam",
42
+ "adam_eps": 1e-06,
43
+ "adam_beta1": 0.9,
44
+ "adam_beta2": 0.999,
45
+ "max_grad_norm": 4.0,
46
+ "learning_rate": 0.0001,
47
+ "lr_schedule": "constant",
48
+ "lr_schedule_kl_threshold": 0.008,
49
+ "lr_adaptive_min": 1e-06,
50
+ "lr_adaptive_max": 0.01,
51
+ "obs_subtract_mean": 0.0,
52
+ "obs_scale": 255.0,
53
+ "normalize_input": true,
54
+ "normalize_input_keys": null,
55
+ "decorrelate_experience_max_seconds": 0,
56
+ "decorrelate_envs_on_one_worker": true,
57
+ "actor_worker_gpus": [],
58
+ "set_workers_cpu_affinity": true,
59
+ "force_envs_single_thread": false,
60
+ "default_niceness": 0,
61
+ "log_to_file": true,
62
+ "experiment_summaries_interval": 10,
63
+ "flush_summaries_interval": 30,
64
+ "stats_avg": 100,
65
+ "summaries_use_frameskip": true,
66
+ "heartbeat_interval": 20,
67
+ "heartbeat_reporting_interval": 600,
68
+ "train_for_env_steps": 4000000,
69
+ "train_for_seconds": 10000000000,
70
+ "save_every_sec": 120,
71
+ "keep_checkpoints": 2,
72
+ "load_checkpoint_kind": "latest",
73
+ "save_milestones_sec": -1,
74
+ "save_best_every_sec": 5,
75
+ "save_best_metric": "reward",
76
+ "save_best_after": 100000,
77
+ "benchmark": false,
78
+ "encoder_mlp_layers": [
79
+ 512,
80
+ 512
81
+ ],
82
+ "encoder_conv_architecture": "convnet_simple",
83
+ "encoder_conv_mlp_layers": [
84
+ 512
85
+ ],
86
+ "use_rnn": true,
87
+ "rnn_size": 512,
88
+ "rnn_type": "gru",
89
+ "rnn_num_layers": 1,
90
+ "decoder_mlp_layers": [],
91
+ "nonlinearity": "elu",
92
+ "policy_initialization": "orthogonal",
93
+ "policy_init_gain": 1.0,
94
+ "actor_critic_share_weights": true,
95
+ "adaptive_stddev": true,
96
+ "continuous_tanh_scale": 0.0,
97
+ "initial_stddev": 1.0,
98
+ "use_env_info_cache": false,
99
+ "env_gpu_actions": false,
100
+ "env_gpu_observations": true,
101
+ "env_frameskip": 4,
102
+ "env_framestack": 1,
103
+ "pixel_format": "CHW",
104
+ "use_record_episode_statistics": false,
105
+ "with_wandb": false,
106
+ "wandb_user": null,
107
+ "wandb_project": "sample_factory",
108
+ "wandb_group": null,
109
+ "wandb_job_type": "SF",
110
+ "wandb_tags": [],
111
+ "with_pbt": false,
112
+ "pbt_mix_policies_in_one_env": true,
113
+ "pbt_period_env_steps": 5000000,
114
+ "pbt_start_mutation": 20000000,
115
+ "pbt_replace_fraction": 0.3,
116
+ "pbt_mutation_rate": 0.15,
117
+ "pbt_replace_reward_gap": 0.1,
118
+ "pbt_replace_reward_gap_absolute": 1e-06,
119
+ "pbt_optimize_gamma": false,
120
+ "pbt_target_objective": "true_objective",
121
+ "pbt_perturb_min": 1.1,
122
+ "pbt_perturb_max": 1.5,
123
+ "num_agents": -1,
124
+ "num_humans": 0,
125
+ "num_bots": -1,
126
+ "start_bot_difficulty": null,
127
+ "timelimit": null,
128
+ "res_w": 128,
129
+ "res_h": 72,
130
+ "wide_aspect_ratio": false,
131
+ "eval_env_frameskip": 1,
132
+ "fps": 35,
133
+ "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000",
134
+ "cli_args": {
135
+ "env": "doom_health_gathering_supreme",
136
+ "num_workers": 8,
137
+ "num_envs_per_worker": 4,
138
+ "train_for_env_steps": 4000000
139
+ },
140
+ "git_hash": "unknown",
141
+ "git_repo_name": "not a git repository"
142
+ }
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e389ac0ec10c9c52440058129cef51a2b4705d2655912b710921b5172dd44690
3
+ size 5177758
sf_log.txt ADDED
@@ -0,0 +1,969 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2024-08-21 20:57:25,004][00286] Saving configuration to /content/train_dir/default_experiment/config.json...
2
+ [2024-08-21 20:57:25,006][00286] Rollout worker 0 uses device cpu
3
+ [2024-08-21 20:57:25,008][00286] Rollout worker 1 uses device cpu
4
+ [2024-08-21 20:57:25,009][00286] Rollout worker 2 uses device cpu
5
+ [2024-08-21 20:57:25,010][00286] Rollout worker 3 uses device cpu
6
+ [2024-08-21 20:57:25,011][00286] Rollout worker 4 uses device cpu
7
+ [2024-08-21 20:57:25,012][00286] Rollout worker 5 uses device cpu
8
+ [2024-08-21 20:57:25,013][00286] Rollout worker 6 uses device cpu
9
+ [2024-08-21 20:57:25,014][00286] Rollout worker 7 uses device cpu
10
+ [2024-08-21 20:57:25,183][00286] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2024-08-21 20:57:25,185][00286] InferenceWorker_p0-w0: min num requests: 2
12
+ [2024-08-21 20:57:25,219][00286] Starting all processes...
13
+ [2024-08-21 20:57:25,220][00286] Starting process learner_proc0
14
+ [2024-08-21 20:57:26,610][00286] Starting all processes...
15
+ [2024-08-21 20:57:26,622][00286] Starting process inference_proc0-0
16
+ [2024-08-21 20:57:26,622][00286] Starting process rollout_proc0
17
+ [2024-08-21 20:57:26,623][00286] Starting process rollout_proc1
18
+ [2024-08-21 20:57:26,623][00286] Starting process rollout_proc2
19
+ [2024-08-21 20:57:26,623][00286] Starting process rollout_proc3
20
+ [2024-08-21 20:57:26,623][00286] Starting process rollout_proc4
21
+ [2024-08-21 20:57:26,623][00286] Starting process rollout_proc5
22
+ [2024-08-21 20:57:26,623][00286] Starting process rollout_proc6
23
+ [2024-08-21 20:57:26,623][00286] Starting process rollout_proc7
24
+ [2024-08-21 20:57:41,211][03216] Worker 2 uses CPU cores [0]
25
+ [2024-08-21 20:57:41,324][03197] Using GPUs [0] for process 0 (actually maps to GPUs [0])
26
+ [2024-08-21 20:57:41,327][03197] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
27
+ [2024-08-21 20:57:41,414][03197] Num visible devices: 1
28
+ [2024-08-21 20:57:41,424][03217] Worker 1 uses CPU cores [1]
29
+ [2024-08-21 20:57:41,441][03197] Starting seed is not provided
30
+ [2024-08-21 20:57:41,442][03197] Using GPUs [0] for process 0 (actually maps to GPUs [0])
31
+ [2024-08-21 20:57:41,443][03197] Initializing actor-critic model on device cuda:0
32
+ [2024-08-21 20:57:41,444][03197] RunningMeanStd input shape: (3, 72, 128)
33
+ [2024-08-21 20:57:41,447][03197] RunningMeanStd input shape: (1,)
34
+ [2024-08-21 20:57:41,472][03221] Worker 7 uses CPU cores [1]
35
+ [2024-08-21 20:57:41,482][03197] ConvEncoder: input_channels=3
36
+ [2024-08-21 20:57:41,524][03219] Worker 5 uses CPU cores [1]
37
+ [2024-08-21 20:57:41,544][03218] Worker 3 uses CPU cores [1]
38
+ [2024-08-21 20:57:41,551][03214] Using GPUs [0] for process 0 (actually maps to GPUs [0])
39
+ [2024-08-21 20:57:41,552][03214] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
40
+ [2024-08-21 20:57:41,604][03214] Num visible devices: 1
41
+ [2024-08-21 20:57:41,655][03222] Worker 6 uses CPU cores [0]
42
+ [2024-08-21 20:57:41,696][03215] Worker 0 uses CPU cores [0]
43
+ [2024-08-21 20:57:41,720][03220] Worker 4 uses CPU cores [0]
44
+ [2024-08-21 20:57:41,815][03197] Conv encoder output size: 512
45
+ [2024-08-21 20:57:41,815][03197] Policy head output size: 512
46
+ [2024-08-21 20:57:41,876][03197] Created Actor Critic model with architecture:
47
+ [2024-08-21 20:57:41,876][03197] ActorCriticSharedWeights(
48
+ (obs_normalizer): ObservationNormalizer(
49
+ (running_mean_std): RunningMeanStdDictInPlace(
50
+ (running_mean_std): ModuleDict(
51
+ (obs): RunningMeanStdInPlace()
52
+ )
53
+ )
54
+ )
55
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
56
+ (encoder): VizdoomEncoder(
57
+ (basic_encoder): ConvEncoder(
58
+ (enc): RecursiveScriptModule(
59
+ original_name=ConvEncoderImpl
60
+ (conv_head): RecursiveScriptModule(
61
+ original_name=Sequential
62
+ (0): RecursiveScriptModule(original_name=Conv2d)
63
+ (1): RecursiveScriptModule(original_name=ELU)
64
+ (2): RecursiveScriptModule(original_name=Conv2d)
65
+ (3): RecursiveScriptModule(original_name=ELU)
66
+ (4): RecursiveScriptModule(original_name=Conv2d)
67
+ (5): RecursiveScriptModule(original_name=ELU)
68
+ )
69
+ (mlp_layers): RecursiveScriptModule(
70
+ original_name=Sequential
71
+ (0): RecursiveScriptModule(original_name=Linear)
72
+ (1): RecursiveScriptModule(original_name=ELU)
73
+ )
74
+ )
75
+ )
76
+ )
77
+ (core): ModelCoreRNN(
78
+ (core): GRU(512, 512)
79
+ )
80
+ (decoder): MlpDecoder(
81
+ (mlp): Identity()
82
+ )
83
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
84
+ (action_parameterization): ActionParameterizationDefault(
85
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
86
+ )
87
+ )
88
+ [2024-08-21 20:57:42,146][03197] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2024-08-21 20:57:42,917][03197] No checkpoints found
90
+ [2024-08-21 20:57:42,917][03197] Did not load from checkpoint, starting from scratch!
91
+ [2024-08-21 20:57:42,917][03197] Initialized policy 0 weights for model version 0
92
+ [2024-08-21 20:57:42,921][03197] Using GPUs [0] for process 0 (actually maps to GPUs [0])
93
+ [2024-08-21 20:57:42,946][03197] LearnerWorker_p0 finished initialization!
94
+ [2024-08-21 20:57:43,067][03214] RunningMeanStd input shape: (3, 72, 128)
95
+ [2024-08-21 20:57:43,068][03214] RunningMeanStd input shape: (1,)
96
+ [2024-08-21 20:57:43,081][03214] ConvEncoder: input_channels=3
97
+ [2024-08-21 20:57:43,188][03214] Conv encoder output size: 512
98
+ [2024-08-21 20:57:43,189][03214] Policy head output size: 512
99
+ [2024-08-21 20:57:43,273][00286] Inference worker 0-0 is ready!
100
+ [2024-08-21 20:57:43,275][00286] All inference workers are ready! Signal rollout workers to start!
101
+ [2024-08-21 20:57:43,718][03221] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2024-08-21 20:57:43,738][03215] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2024-08-21 20:57:43,763][03216] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2024-08-21 20:57:43,780][03220] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2024-08-21 20:57:43,781][03222] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2024-08-21 20:57:43,834][03217] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2024-08-21 20:57:43,842][03219] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2024-08-21 20:57:43,866][03218] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2024-08-21 20:57:45,175][00286] Heartbeat connected on Batcher_0
110
+ [2024-08-21 20:57:45,181][00286] Heartbeat connected on LearnerWorker_p0
111
+ [2024-08-21 20:57:45,210][00286] Heartbeat connected on InferenceWorker_p0-w0
112
+ [2024-08-21 20:57:45,793][00286] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
113
+ [2024-08-21 20:57:46,263][03216] Decorrelating experience for 0 frames...
114
+ [2024-08-21 20:57:46,264][03219] Decorrelating experience for 0 frames...
115
+ [2024-08-21 20:57:46,269][03220] Decorrelating experience for 0 frames...
116
+ [2024-08-21 20:57:46,262][03217] Decorrelating experience for 0 frames...
117
+ [2024-08-21 20:57:46,265][03221] Decorrelating experience for 0 frames...
118
+ [2024-08-21 20:57:46,271][03215] Decorrelating experience for 0 frames...
119
+ [2024-08-21 20:57:46,273][03222] Decorrelating experience for 0 frames...
120
+ [2024-08-21 20:57:46,985][03216] Decorrelating experience for 32 frames...
121
+ [2024-08-21 20:57:47,586][03218] Decorrelating experience for 0 frames...
122
+ [2024-08-21 20:57:47,603][03217] Decorrelating experience for 32 frames...
123
+ [2024-08-21 20:57:47,605][03219] Decorrelating experience for 32 frames...
124
+ [2024-08-21 20:57:48,445][03215] Decorrelating experience for 32 frames...
125
+ [2024-08-21 20:57:49,399][03218] Decorrelating experience for 32 frames...
126
+ [2024-08-21 20:57:49,404][03220] Decorrelating experience for 32 frames...
127
+ [2024-08-21 20:57:49,416][03221] Decorrelating experience for 32 frames...
128
+ [2024-08-21 20:57:49,723][03215] Decorrelating experience for 64 frames...
129
+ [2024-08-21 20:57:49,908][03217] Decorrelating experience for 64 frames...
130
+ [2024-08-21 20:57:49,931][03219] Decorrelating experience for 64 frames...
131
+ [2024-08-21 20:57:50,701][03216] Decorrelating experience for 64 frames...
132
+ [2024-08-21 20:57:50,793][00286] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
133
+ [2024-08-21 20:57:50,810][03218] Decorrelating experience for 64 frames...
134
+ [2024-08-21 20:57:50,854][03219] Decorrelating experience for 96 frames...
135
+ [2024-08-21 20:57:50,997][00286] Heartbeat connected on RolloutWorker_w5
136
+ [2024-08-21 20:57:51,223][03220] Decorrelating experience for 64 frames...
137
+ [2024-08-21 20:57:51,318][03215] Decorrelating experience for 96 frames...
138
+ [2024-08-21 20:57:51,654][03218] Decorrelating experience for 96 frames...
139
+ [2024-08-21 20:57:51,670][00286] Heartbeat connected on RolloutWorker_w0
140
+ [2024-08-21 20:57:51,870][00286] Heartbeat connected on RolloutWorker_w3
141
+ [2024-08-21 20:57:52,402][03217] Decorrelating experience for 96 frames...
142
+ [2024-08-21 20:57:52,571][03221] Decorrelating experience for 64 frames...
143
+ [2024-08-21 20:57:52,615][00286] Heartbeat connected on RolloutWorker_w1
144
+ [2024-08-21 20:57:53,060][03222] Decorrelating experience for 32 frames...
145
+ [2024-08-21 20:57:53,188][03216] Decorrelating experience for 96 frames...
146
+ [2024-08-21 20:57:53,430][00286] Heartbeat connected on RolloutWorker_w2
147
+ [2024-08-21 20:57:53,761][03220] Decorrelating experience for 96 frames...
148
+ [2024-08-21 20:57:53,984][00286] Heartbeat connected on RolloutWorker_w4
149
+ [2024-08-21 20:57:55,793][00286] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 179.2. Samples: 1792. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
150
+ [2024-08-21 20:57:55,796][00286] Avg episode reward: [(0, '2.106')]
151
+ [2024-08-21 20:57:56,012][03221] Decorrelating experience for 96 frames...
152
+ [2024-08-21 20:57:56,428][03197] Signal inference workers to stop experience collection...
153
+ [2024-08-21 20:57:56,456][03214] InferenceWorker_p0-w0: stopping experience collection
154
+ [2024-08-21 20:57:56,544][00286] Heartbeat connected on RolloutWorker_w7
155
+ [2024-08-21 20:57:56,740][03222] Decorrelating experience for 64 frames...
156
+ [2024-08-21 20:57:57,844][03222] Decorrelating experience for 96 frames...
157
+ [2024-08-21 20:57:57,955][00286] Heartbeat connected on RolloutWorker_w6
158
+ [2024-08-21 20:57:59,437][03197] Signal inference workers to resume experience collection...
159
+ [2024-08-21 20:57:59,438][03214] InferenceWorker_p0-w0: resuming experience collection
160
+ [2024-08-21 20:58:00,796][00286] Fps is (10 sec: 409.5, 60 sec: 273.0, 300 sec: 273.0). Total num frames: 4096. Throughput: 0: 167.2. Samples: 2508. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
161
+ [2024-08-21 20:58:00,799][00286] Avg episode reward: [(0, '2.837')]
162
+ [2024-08-21 20:58:05,793][00286] Fps is (10 sec: 2048.0, 60 sec: 1024.0, 300 sec: 1024.0). Total num frames: 20480. Throughput: 0: 256.6. Samples: 5132. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
163
+ [2024-08-21 20:58:05,799][00286] Avg episode reward: [(0, '3.556')]
164
+ [2024-08-21 20:58:09,745][03214] Updated weights for policy 0, policy_version 10 (0.0036)
165
+ [2024-08-21 20:58:10,793][00286] Fps is (10 sec: 4097.1, 60 sec: 1802.2, 300 sec: 1802.2). Total num frames: 45056. Throughput: 0: 449.6. Samples: 11240. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
166
+ [2024-08-21 20:58:10,798][00286] Avg episode reward: [(0, '4.197')]
167
+ [2024-08-21 20:58:15,793][00286] Fps is (10 sec: 4505.6, 60 sec: 2184.5, 300 sec: 2184.5). Total num frames: 65536. Throughput: 0: 491.9. Samples: 14756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
168
+ [2024-08-21 20:58:15,799][00286] Avg episode reward: [(0, '4.332')]
169
+ [2024-08-21 20:58:20,793][00286] Fps is (10 sec: 3276.6, 60 sec: 2223.5, 300 sec: 2223.5). Total num frames: 77824. Throughput: 0: 568.5. Samples: 19898. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
170
+ [2024-08-21 20:58:20,795][00286] Avg episode reward: [(0, '4.287')]
171
+ [2024-08-21 20:58:20,928][03214] Updated weights for policy 0, policy_version 20 (0.0036)
172
+ [2024-08-21 20:58:25,793][00286] Fps is (10 sec: 3276.8, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 98304. Throughput: 0: 630.8. Samples: 25230. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
173
+ [2024-08-21 20:58:25,800][00286] Avg episode reward: [(0, '4.298')]
174
+ [2024-08-21 20:58:30,793][00286] Fps is (10 sec: 4096.2, 60 sec: 2639.6, 300 sec: 2639.6). Total num frames: 118784. Throughput: 0: 636.0. Samples: 28618. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
175
+ [2024-08-21 20:58:30,799][00286] Avg episode reward: [(0, '4.459')]
176
+ [2024-08-21 20:58:30,881][03197] Saving new best policy, reward=4.459!
177
+ [2024-08-21 20:58:30,897][03214] Updated weights for policy 0, policy_version 30 (0.0030)
178
+ [2024-08-21 20:58:35,794][00286] Fps is (10 sec: 4095.7, 60 sec: 2785.2, 300 sec: 2785.2). Total num frames: 139264. Throughput: 0: 765.4. Samples: 34442. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
179
+ [2024-08-21 20:58:35,797][00286] Avg episode reward: [(0, '4.542')]
180
+ [2024-08-21 20:58:35,806][03197] Saving new best policy, reward=4.542!
181
+ [2024-08-21 20:58:40,793][00286] Fps is (10 sec: 3276.8, 60 sec: 2755.5, 300 sec: 2755.5). Total num frames: 151552. Throughput: 0: 810.8. Samples: 38280. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
182
+ [2024-08-21 20:58:40,798][00286] Avg episode reward: [(0, '4.383')]
183
+ [2024-08-21 20:58:43,427][03214] Updated weights for policy 0, policy_version 40 (0.0027)
184
+ [2024-08-21 20:58:45,793][00286] Fps is (10 sec: 3277.0, 60 sec: 2867.2, 300 sec: 2867.2). Total num frames: 172032. Throughput: 0: 866.3. Samples: 41490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
185
+ [2024-08-21 20:58:45,796][00286] Avg episode reward: [(0, '4.310')]
186
+ [2024-08-21 20:58:50,796][00286] Fps is (10 sec: 4094.9, 60 sec: 3208.4, 300 sec: 2961.6). Total num frames: 192512. Throughput: 0: 950.7. Samples: 47918. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
187
+ [2024-08-21 20:58:50,804][00286] Avg episode reward: [(0, '4.352')]
188
+ [2024-08-21 20:58:54,474][03214] Updated weights for policy 0, policy_version 50 (0.0040)
189
+ [2024-08-21 20:58:55,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 2925.7). Total num frames: 204800. Throughput: 0: 909.7. Samples: 52178. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
190
+ [2024-08-21 20:58:55,797][00286] Avg episode reward: [(0, '4.468')]
191
+ [2024-08-21 20:59:00,793][00286] Fps is (10 sec: 3277.6, 60 sec: 3686.6, 300 sec: 3003.7). Total num frames: 225280. Throughput: 0: 884.5. Samples: 54560. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
192
+ [2024-08-21 20:59:00,796][00286] Avg episode reward: [(0, '4.469')]
193
+ [2024-08-21 20:59:05,167][03214] Updated weights for policy 0, policy_version 60 (0.0025)
194
+ [2024-08-21 20:59:05,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3072.0). Total num frames: 245760. Throughput: 0: 915.9. Samples: 61114. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
195
+ [2024-08-21 20:59:05,797][00286] Avg episode reward: [(0, '4.547')]
196
+ [2024-08-21 20:59:05,799][03197] Saving new best policy, reward=4.547!
197
+ [2024-08-21 20:59:10,795][00286] Fps is (10 sec: 3685.9, 60 sec: 3618.0, 300 sec: 3084.0). Total num frames: 262144. Throughput: 0: 914.6. Samples: 66390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
198
+ [2024-08-21 20:59:10,797][00286] Avg episode reward: [(0, '4.503')]
199
+ [2024-08-21 20:59:15,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3094.8). Total num frames: 278528. Throughput: 0: 882.1. Samples: 68314. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
200
+ [2024-08-21 20:59:15,798][00286] Avg episode reward: [(0, '4.441')]
201
+ [2024-08-21 20:59:17,384][03214] Updated weights for policy 0, policy_version 70 (0.0025)
202
+ [2024-08-21 20:59:20,793][00286] Fps is (10 sec: 3687.0, 60 sec: 3686.4, 300 sec: 3147.4). Total num frames: 299008. Throughput: 0: 885.7. Samples: 74298. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
203
+ [2024-08-21 20:59:20,798][00286] Avg episode reward: [(0, '4.530')]
204
+ [2024-08-21 20:59:20,809][03197] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000073_299008.pth...
205
+ [2024-08-21 20:59:25,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3194.9). Total num frames: 319488. Throughput: 0: 936.8. Samples: 80438. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
206
+ [2024-08-21 20:59:25,798][00286] Avg episode reward: [(0, '4.484')]
207
+ [2024-08-21 20:59:28,396][03214] Updated weights for policy 0, policy_version 80 (0.0020)
208
+ [2024-08-21 20:59:30,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3159.8). Total num frames: 331776. Throughput: 0: 909.6. Samples: 82420. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
209
+ [2024-08-21 20:59:30,799][00286] Avg episode reward: [(0, '4.350')]
210
+ [2024-08-21 20:59:35,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3202.3). Total num frames: 352256. Throughput: 0: 881.0. Samples: 87562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
211
+ [2024-08-21 20:59:35,796][00286] Avg episode reward: [(0, '4.396')]
212
+ [2024-08-21 20:59:38,680][03214] Updated weights for policy 0, policy_version 90 (0.0023)
213
+ [2024-08-21 20:59:40,793][00286] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3276.8). Total num frames: 376832. Throughput: 0: 939.4. Samples: 94452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
214
+ [2024-08-21 20:59:40,796][00286] Avg episode reward: [(0, '4.391')]
215
+ [2024-08-21 20:59:45,796][00286] Fps is (10 sec: 4094.9, 60 sec: 3686.2, 300 sec: 3276.7). Total num frames: 393216. Throughput: 0: 953.1. Samples: 97452. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
216
+ [2024-08-21 20:59:45,799][00286] Avg episode reward: [(0, '4.404')]
217
+ [2024-08-21 20:59:50,263][03214] Updated weights for policy 0, policy_version 100 (0.0018)
218
+ [2024-08-21 20:59:50,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3618.3, 300 sec: 3276.8). Total num frames: 409600. Throughput: 0: 903.4. Samples: 101768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
219
+ [2024-08-21 20:59:50,795][00286] Avg episode reward: [(0, '4.451')]
220
+ [2024-08-21 20:59:55,793][00286] Fps is (10 sec: 4097.1, 60 sec: 3822.9, 300 sec: 3339.8). Total num frames: 434176. Throughput: 0: 942.0. Samples: 108778. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
221
+ [2024-08-21 20:59:55,800][00286] Avg episode reward: [(0, '4.512')]
222
+ [2024-08-21 20:59:59,184][03214] Updated weights for policy 0, policy_version 110 (0.0016)
223
+ [2024-08-21 21:00:00,793][00286] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3367.8). Total num frames: 454656. Throughput: 0: 977.5. Samples: 112300. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
224
+ [2024-08-21 21:00:00,799][00286] Avg episode reward: [(0, '4.587')]
225
+ [2024-08-21 21:00:00,810][03197] Saving new best policy, reward=4.587!
226
+ [2024-08-21 21:00:05,795][00286] Fps is (10 sec: 3276.2, 60 sec: 3686.3, 300 sec: 3335.3). Total num frames: 466944. Throughput: 0: 945.5. Samples: 116846. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
227
+ [2024-08-21 21:00:05,798][00286] Avg episode reward: [(0, '4.472')]
228
+ [2024-08-21 21:00:10,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3361.5). Total num frames: 487424. Throughput: 0: 939.0. Samples: 122694. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
229
+ [2024-08-21 21:00:10,797][00286] Avg episode reward: [(0, '4.339')]
230
+ [2024-08-21 21:00:11,029][03214] Updated weights for policy 0, policy_version 120 (0.0056)
231
+ [2024-08-21 21:00:15,793][00286] Fps is (10 sec: 4506.4, 60 sec: 3891.2, 300 sec: 3413.3). Total num frames: 512000. Throughput: 0: 973.3. Samples: 126220. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
232
+ [2024-08-21 21:00:15,795][00286] Avg episode reward: [(0, '4.502')]
233
+ [2024-08-21 21:00:20,794][00286] Fps is (10 sec: 4095.7, 60 sec: 3822.9, 300 sec: 3408.9). Total num frames: 528384. Throughput: 0: 990.5. Samples: 132134. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
234
+ [2024-08-21 21:00:20,797][00286] Avg episode reward: [(0, '4.582')]
235
+ [2024-08-21 21:00:21,339][03214] Updated weights for policy 0, policy_version 130 (0.0036)
236
+ [2024-08-21 21:00:25,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3404.8). Total num frames: 544768. Throughput: 0: 943.1. Samples: 136892. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
237
+ [2024-08-21 21:00:25,800][00286] Avg episode reward: [(0, '4.536')]
238
+ [2024-08-21 21:00:30,793][00286] Fps is (10 sec: 4096.3, 60 sec: 3959.5, 300 sec: 3450.6). Total num frames: 569344. Throughput: 0: 952.9. Samples: 140330. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
239
+ [2024-08-21 21:00:30,799][00286] Avg episode reward: [(0, '4.460')]
240
+ [2024-08-21 21:00:31,571][03214] Updated weights for policy 0, policy_version 140 (0.0030)
241
+ [2024-08-21 21:00:35,793][00286] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3469.6). Total num frames: 589824. Throughput: 0: 1007.5. Samples: 147104. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
242
+ [2024-08-21 21:00:35,796][00286] Avg episode reward: [(0, '4.414')]
243
+ [2024-08-21 21:00:40,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3440.6). Total num frames: 602112. Throughput: 0: 944.8. Samples: 151294. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
244
+ [2024-08-21 21:00:40,795][00286] Avg episode reward: [(0, '4.398')]
245
+ [2024-08-21 21:00:43,307][03214] Updated weights for policy 0, policy_version 150 (0.0031)
246
+ [2024-08-21 21:00:45,793][00286] Fps is (10 sec: 3276.7, 60 sec: 3823.1, 300 sec: 3458.8). Total num frames: 622592. Throughput: 0: 930.9. Samples: 154190. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
247
+ [2024-08-21 21:00:45,799][00286] Avg episode reward: [(0, '4.218')]
248
+ [2024-08-21 21:00:50,793][00286] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3498.2). Total num frames: 647168. Throughput: 0: 981.4. Samples: 161008. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
249
+ [2024-08-21 21:00:50,796][00286] Avg episode reward: [(0, '4.429')]
250
+ [2024-08-21 21:00:53,020][03214] Updated weights for policy 0, policy_version 160 (0.0018)
251
+ [2024-08-21 21:00:55,793][00286] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3470.8). Total num frames: 659456. Throughput: 0: 964.9. Samples: 166116. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
252
+ [2024-08-21 21:00:55,794][00286] Avg episode reward: [(0, '4.558')]
253
+ [2024-08-21 21:01:00,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3486.9). Total num frames: 679936. Throughput: 0: 935.2. Samples: 168302. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
254
+ [2024-08-21 21:01:00,800][00286] Avg episode reward: [(0, '4.511')]
255
+ [2024-08-21 21:01:04,107][03214] Updated weights for policy 0, policy_version 170 (0.0044)
256
+ [2024-08-21 21:01:05,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3891.3, 300 sec: 3502.1). Total num frames: 700416. Throughput: 0: 949.6. Samples: 174864. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
257
+ [2024-08-21 21:01:05,795][00286] Avg episode reward: [(0, '4.499')]
258
+ [2024-08-21 21:01:10,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3516.6). Total num frames: 720896. Throughput: 0: 972.9. Samples: 180672. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
259
+ [2024-08-21 21:01:10,795][00286] Avg episode reward: [(0, '4.446')]
260
+ [2024-08-21 21:01:15,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3491.4). Total num frames: 733184. Throughput: 0: 938.0. Samples: 182540. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
261
+ [2024-08-21 21:01:15,798][00286] Avg episode reward: [(0, '4.304')]
262
+ [2024-08-21 21:01:16,309][03214] Updated weights for policy 0, policy_version 180 (0.0019)
263
+ [2024-08-21 21:01:20,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3505.4). Total num frames: 753664. Throughput: 0: 909.0. Samples: 188008. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
264
+ [2024-08-21 21:01:20,797][00286] Avg episode reward: [(0, '4.570')]
265
+ [2024-08-21 21:01:20,807][03197] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000184_753664.pth...
266
+ [2024-08-21 21:01:25,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3518.8). Total num frames: 774144. Throughput: 0: 959.8. Samples: 194484. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
267
+ [2024-08-21 21:01:25,798][00286] Avg episode reward: [(0, '4.722')]
268
+ [2024-08-21 21:01:25,868][03197] Saving new best policy, reward=4.722!
269
+ [2024-08-21 21:01:25,875][03214] Updated weights for policy 0, policy_version 190 (0.0035)
270
+ [2024-08-21 21:01:30,797][00286] Fps is (10 sec: 3685.0, 60 sec: 3686.2, 300 sec: 3513.4). Total num frames: 790528. Throughput: 0: 943.8. Samples: 196664. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
271
+ [2024-08-21 21:01:30,799][00286] Avg episode reward: [(0, '4.729')]
272
+ [2024-08-21 21:01:30,815][03197] Saving new best policy, reward=4.729!
273
+ [2024-08-21 21:01:35,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3508.3). Total num frames: 806912. Throughput: 0: 891.7. Samples: 201134. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
274
+ [2024-08-21 21:01:35,795][00286] Avg episode reward: [(0, '4.548')]
275
+ [2024-08-21 21:01:38,390][03214] Updated weights for policy 0, policy_version 200 (0.0025)
276
+ [2024-08-21 21:01:40,793][00286] Fps is (10 sec: 3687.8, 60 sec: 3754.7, 300 sec: 3520.8). Total num frames: 827392. Throughput: 0: 920.4. Samples: 207534. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
277
+ [2024-08-21 21:01:40,800][00286] Avg episode reward: [(0, '4.602')]
278
+ [2024-08-21 21:01:45,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3515.7). Total num frames: 843776. Throughput: 0: 940.9. Samples: 210644. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
279
+ [2024-08-21 21:01:45,795][00286] Avg episode reward: [(0, '4.556')]
280
+ [2024-08-21 21:01:50,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3494.1). Total num frames: 856064. Throughput: 0: 878.3. Samples: 214388. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
281
+ [2024-08-21 21:01:50,800][00286] Avg episode reward: [(0, '4.568')]
282
+ [2024-08-21 21:01:50,913][03214] Updated weights for policy 0, policy_version 210 (0.0023)
283
+ [2024-08-21 21:01:55,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3522.6). Total num frames: 880640. Throughput: 0: 879.6. Samples: 220254. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
284
+ [2024-08-21 21:01:55,795][00286] Avg episode reward: [(0, '4.447')]
285
+ [2024-08-21 21:02:00,421][03214] Updated weights for policy 0, policy_version 220 (0.0029)
286
+ [2024-08-21 21:02:00,793][00286] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3533.8). Total num frames: 901120. Throughput: 0: 911.2. Samples: 223544. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
287
+ [2024-08-21 21:02:00,795][00286] Avg episode reward: [(0, '4.346')]
288
+ [2024-08-21 21:02:05,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3513.1). Total num frames: 913408. Throughput: 0: 895.7. Samples: 228316. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
289
+ [2024-08-21 21:02:05,797][00286] Avg episode reward: [(0, '4.632')]
290
+ [2024-08-21 21:02:10,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3508.6). Total num frames: 929792. Throughput: 0: 858.3. Samples: 233106. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
291
+ [2024-08-21 21:02:10,800][00286] Avg episode reward: [(0, '4.572')]
292
+ [2024-08-21 21:02:12,996][03214] Updated weights for policy 0, policy_version 230 (0.0029)
293
+ [2024-08-21 21:02:15,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3519.5). Total num frames: 950272. Throughput: 0: 881.1. Samples: 236310. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
294
+ [2024-08-21 21:02:15,798][00286] Avg episode reward: [(0, '4.622')]
295
+ [2024-08-21 21:02:20,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3530.0). Total num frames: 970752. Throughput: 0: 917.6. Samples: 242426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
296
+ [2024-08-21 21:02:20,795][00286] Avg episode reward: [(0, '4.617')]
297
+ [2024-08-21 21:02:25,039][03214] Updated weights for policy 0, policy_version 240 (0.0034)
298
+ [2024-08-21 21:02:25,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3510.9). Total num frames: 983040. Throughput: 0: 867.7. Samples: 246580. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
299
+ [2024-08-21 21:02:25,795][00286] Avg episode reward: [(0, '4.463')]
300
+ [2024-08-21 21:02:30,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3521.1). Total num frames: 1003520. Throughput: 0: 867.5. Samples: 249682. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
301
+ [2024-08-21 21:02:30,799][00286] Avg episode reward: [(0, '4.453')]
302
+ [2024-08-21 21:02:35,068][03214] Updated weights for policy 0, policy_version 250 (0.0022)
303
+ [2024-08-21 21:02:35,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3531.0). Total num frames: 1024000. Throughput: 0: 920.2. Samples: 255798. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
304
+ [2024-08-21 21:02:35,795][00286] Avg episode reward: [(0, '4.687')]
305
+ [2024-08-21 21:02:40,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 1036288. Throughput: 0: 880.8. Samples: 259890. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
306
+ [2024-08-21 21:02:40,800][00286] Avg episode reward: [(0, '4.699')]
307
+ [2024-08-21 21:02:45,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 1056768. Throughput: 0: 859.2. Samples: 262208. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
308
+ [2024-08-21 21:02:45,800][00286] Avg episode reward: [(0, '4.676')]
309
+ [2024-08-21 21:02:47,857][03214] Updated weights for policy 0, policy_version 260 (0.0025)
310
+ [2024-08-21 21:02:50,793][00286] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1077248. Throughput: 0: 892.8. Samples: 268492. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
311
+ [2024-08-21 21:02:50,795][00286] Avg episode reward: [(0, '4.592')]
312
+ [2024-08-21 21:02:55,793][00286] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 1089536. Throughput: 0: 899.2. Samples: 273570. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
313
+ [2024-08-21 21:02:55,796][00286] Avg episode reward: [(0, '4.587')]
314
+ [2024-08-21 21:03:00,259][03214] Updated weights for policy 0, policy_version 270 (0.0021)
315
+ [2024-08-21 21:03:00,793][00286] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 3679.5). Total num frames: 1105920. Throughput: 0: 871.0. Samples: 275504. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
316
+ [2024-08-21 21:03:00,801][00286] Avg episode reward: [(0, '4.493')]
317
+ [2024-08-21 21:03:05,793][00286] Fps is (10 sec: 3686.5, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 1126400. Throughput: 0: 865.6. Samples: 281376. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
318
+ [2024-08-21 21:03:05,795][00286] Avg episode reward: [(0, '4.453')]
319
+ [2024-08-21 21:03:09,410][03214] Updated weights for policy 0, policy_version 280 (0.0022)
320
+ [2024-08-21 21:03:10,793][00286] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1150976. Throughput: 0: 920.2. Samples: 287988. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
321
+ [2024-08-21 21:03:10,796][00286] Avg episode reward: [(0, '4.547')]
322
+ [2024-08-21 21:03:15,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 1163264. Throughput: 0: 899.2. Samples: 290144. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
323
+ [2024-08-21 21:03:15,801][00286] Avg episode reward: [(0, '4.799')]
324
+ [2024-08-21 21:03:15,802][03197] Saving new best policy, reward=4.799!
325
+ [2024-08-21 21:03:20,793][00286] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 1183744. Throughput: 0: 879.8. Samples: 295390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
326
+ [2024-08-21 21:03:20,797][00286] Avg episode reward: [(0, '4.723')]
327
+ [2024-08-21 21:03:20,811][03197] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000289_1183744.pth...
328
+ [2024-08-21 21:03:20,931][03197] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000073_299008.pth
329
+ [2024-08-21 21:03:21,149][03214] Updated weights for policy 0, policy_version 290 (0.0014)
330
+ [2024-08-21 21:03:25,793][00286] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1208320. Throughput: 0: 944.0. Samples: 302372. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
331
+ [2024-08-21 21:03:25,801][00286] Avg episode reward: [(0, '4.635')]
332
+ [2024-08-21 21:03:30,794][00286] Fps is (10 sec: 4095.6, 60 sec: 3686.3, 300 sec: 3679.5). Total num frames: 1224704. Throughput: 0: 955.4. Samples: 305202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
333
+ [2024-08-21 21:03:30,796][00286] Avg episode reward: [(0, '4.446')]
334
+ [2024-08-21 21:03:32,106][03214] Updated weights for policy 0, policy_version 300 (0.0017)
335
+ [2024-08-21 21:03:35,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 1241088. Throughput: 0: 908.4. Samples: 309370. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
336
+ [2024-08-21 21:03:35,800][00286] Avg episode reward: [(0, '4.832')]
337
+ [2024-08-21 21:03:35,803][03197] Saving new best policy, reward=4.832!
338
+ [2024-08-21 21:03:40,793][00286] Fps is (10 sec: 3686.6, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1261568. Throughput: 0: 941.0. Samples: 315916. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
339
+ [2024-08-21 21:03:40,796][00286] Avg episode reward: [(0, '4.931')]
340
+ [2024-08-21 21:03:40,808][03197] Saving new best policy, reward=4.931!
341
+ [2024-08-21 21:03:42,325][03214] Updated weights for policy 0, policy_version 310 (0.0023)
342
+ [2024-08-21 21:03:45,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3693.4). Total num frames: 1282048. Throughput: 0: 968.6. Samples: 319092. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
343
+ [2024-08-21 21:03:45,799][00286] Avg episode reward: [(0, '4.872')]
344
+ [2024-08-21 21:03:50,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 1294336. Throughput: 0: 942.5. Samples: 323788. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
345
+ [2024-08-21 21:03:50,800][00286] Avg episode reward: [(0, '4.853')]
346
+ [2024-08-21 21:03:54,229][03214] Updated weights for policy 0, policy_version 320 (0.0034)
347
+ [2024-08-21 21:03:55,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1314816. Throughput: 0: 922.8. Samples: 329512. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
348
+ [2024-08-21 21:03:55,796][00286] Avg episode reward: [(0, '4.775')]
349
+ [2024-08-21 21:04:00,793][00286] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 1335296. Throughput: 0: 947.5. Samples: 332780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
350
+ [2024-08-21 21:04:00,803][00286] Avg episode reward: [(0, '4.609')]
351
+ [2024-08-21 21:04:04,545][03214] Updated weights for policy 0, policy_version 330 (0.0031)
352
+ [2024-08-21 21:04:05,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3693.4). Total num frames: 1351680. Throughput: 0: 953.0. Samples: 338274. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
353
+ [2024-08-21 21:04:05,799][00286] Avg episode reward: [(0, '4.749')]
354
+ [2024-08-21 21:04:10,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3693.3). Total num frames: 1368064. Throughput: 0: 893.6. Samples: 342586. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
355
+ [2024-08-21 21:04:10,802][00286] Avg episode reward: [(0, '4.805')]
356
+ [2024-08-21 21:04:15,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1388544. Throughput: 0: 902.9. Samples: 345830. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
357
+ [2024-08-21 21:04:15,795][00286] Avg episode reward: [(0, '4.783')]
358
+ [2024-08-21 21:04:15,834][03214] Updated weights for policy 0, policy_version 340 (0.0031)
359
+ [2024-08-21 21:04:20,798][00286] Fps is (10 sec: 4094.1, 60 sec: 3754.4, 300 sec: 3693.3). Total num frames: 1409024. Throughput: 0: 959.1. Samples: 352534. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
360
+ [2024-08-21 21:04:20,800][00286] Avg episode reward: [(0, '4.514')]
361
+ [2024-08-21 21:04:25,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 1425408. Throughput: 0: 904.0. Samples: 356596. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
362
+ [2024-08-21 21:04:25,799][00286] Avg episode reward: [(0, '4.449')]
363
+ [2024-08-21 21:04:28,138][03214] Updated weights for policy 0, policy_version 350 (0.0025)
364
+ [2024-08-21 21:04:30,793][00286] Fps is (10 sec: 3278.3, 60 sec: 3618.2, 300 sec: 3693.3). Total num frames: 1441792. Throughput: 0: 893.2. Samples: 359284. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
365
+ [2024-08-21 21:04:30,795][00286] Avg episode reward: [(0, '4.323')]
366
+ [2024-08-21 21:04:35,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1466368. Throughput: 0: 928.4. Samples: 365564. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
367
+ [2024-08-21 21:04:35,795][00286] Avg episode reward: [(0, '4.564')]
368
+ [2024-08-21 21:04:38,708][03214] Updated weights for policy 0, policy_version 360 (0.0024)
369
+ [2024-08-21 21:04:40,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 1478656. Throughput: 0: 906.0. Samples: 370282. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
370
+ [2024-08-21 21:04:40,800][00286] Avg episode reward: [(0, '4.856')]
371
+ [2024-08-21 21:04:45,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 1495040. Throughput: 0: 876.6. Samples: 372228. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
372
+ [2024-08-21 21:04:45,799][00286] Avg episode reward: [(0, '4.814')]
373
+ [2024-08-21 21:04:50,358][03214] Updated weights for policy 0, policy_version 370 (0.0021)
374
+ [2024-08-21 21:04:50,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1515520. Throughput: 0: 890.9. Samples: 378364. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
375
+ [2024-08-21 21:04:50,795][00286] Avg episode reward: [(0, '4.520')]
376
+ [2024-08-21 21:04:55,795][00286] Fps is (10 sec: 4095.3, 60 sec: 3686.3, 300 sec: 3665.6). Total num frames: 1536000. Throughput: 0: 923.7. Samples: 384152. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
377
+ [2024-08-21 21:04:55,797][00286] Avg episode reward: [(0, '4.371')]
378
+ [2024-08-21 21:05:00,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 1548288. Throughput: 0: 893.5. Samples: 386036. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
379
+ [2024-08-21 21:05:00,795][00286] Avg episode reward: [(0, '4.381')]
380
+ [2024-08-21 21:05:02,521][03214] Updated weights for policy 0, policy_version 380 (0.0032)
381
+ [2024-08-21 21:05:05,793][00286] Fps is (10 sec: 3277.3, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1568768. Throughput: 0: 863.4. Samples: 391382. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
382
+ [2024-08-21 21:05:05,800][00286] Avg episode reward: [(0, '4.561')]
383
+ [2024-08-21 21:05:10,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1589248. Throughput: 0: 916.5. Samples: 397838. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
384
+ [2024-08-21 21:05:10,796][00286] Avg episode reward: [(0, '4.514')]
385
+ [2024-08-21 21:05:13,088][03214] Updated weights for policy 0, policy_version 390 (0.0041)
386
+ [2024-08-21 21:05:15,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1601536. Throughput: 0: 904.1. Samples: 399970. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
387
+ [2024-08-21 21:05:15,796][00286] Avg episode reward: [(0, '4.478')]
388
+ [2024-08-21 21:05:20,796][00286] Fps is (10 sec: 3275.9, 60 sec: 3550.0, 300 sec: 3651.7). Total num frames: 1622016. Throughput: 0: 865.4. Samples: 404508. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
389
+ [2024-08-21 21:05:20,800][00286] Avg episode reward: [(0, '4.586')]
390
+ [2024-08-21 21:05:20,816][03197] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000396_1622016.pth...
391
+ [2024-08-21 21:05:20,967][03197] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000184_753664.pth
392
+ [2024-08-21 21:05:24,394][03214] Updated weights for policy 0, policy_version 400 (0.0027)
393
+ [2024-08-21 21:05:25,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1642496. Throughput: 0: 904.5. Samples: 410984. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
394
+ [2024-08-21 21:05:25,798][00286] Avg episode reward: [(0, '4.758')]
395
+ [2024-08-21 21:05:30,793][00286] Fps is (10 sec: 3687.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1658880. Throughput: 0: 931.6. Samples: 414152. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
396
+ [2024-08-21 21:05:30,799][00286] Avg episode reward: [(0, '4.653')]
397
+ [2024-08-21 21:05:35,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 1675264. Throughput: 0: 885.8. Samples: 418226. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
398
+ [2024-08-21 21:05:35,797][00286] Avg episode reward: [(0, '4.840')]
399
+ [2024-08-21 21:05:36,643][03214] Updated weights for policy 0, policy_version 410 (0.0043)
400
+ [2024-08-21 21:05:40,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1695744. Throughput: 0: 892.8. Samples: 424328. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
401
+ [2024-08-21 21:05:40,795][00286] Avg episode reward: [(0, '4.892')]
402
+ [2024-08-21 21:05:45,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 1716224. Throughput: 0: 925.8. Samples: 427696. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
403
+ [2024-08-21 21:05:45,795][00286] Avg episode reward: [(0, '4.766')]
404
+ [2024-08-21 21:05:46,052][03214] Updated weights for policy 0, policy_version 420 (0.0033)
405
+ [2024-08-21 21:05:50,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1732608. Throughput: 0: 920.2. Samples: 432792. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
406
+ [2024-08-21 21:05:50,803][00286] Avg episode reward: [(0, '4.631')]
407
+ [2024-08-21 21:05:55,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3550.0, 300 sec: 3623.9). Total num frames: 1748992. Throughput: 0: 892.0. Samples: 437978. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
408
+ [2024-08-21 21:05:55,799][00286] Avg episode reward: [(0, '4.812')]
409
+ [2024-08-21 21:05:57,807][03214] Updated weights for policy 0, policy_version 430 (0.0028)
410
+ [2024-08-21 21:06:00,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 1773568. Throughput: 0: 919.3. Samples: 441338. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
411
+ [2024-08-21 21:06:00,800][00286] Avg episode reward: [(0, '4.980')]
412
+ [2024-08-21 21:06:00,810][03197] Saving new best policy, reward=4.980!
413
+ [2024-08-21 21:06:05,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 1789952. Throughput: 0: 952.7. Samples: 447378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
414
+ [2024-08-21 21:06:05,795][00286] Avg episode reward: [(0, '4.824')]
415
+ [2024-08-21 21:06:09,737][03214] Updated weights for policy 0, policy_version 440 (0.0044)
416
+ [2024-08-21 21:06:10,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3623.9). Total num frames: 1802240. Throughput: 0: 901.2. Samples: 451540. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
417
+ [2024-08-21 21:06:10,800][00286] Avg episode reward: [(0, '4.985')]
418
+ [2024-08-21 21:06:10,911][03197] Saving new best policy, reward=4.985!
419
+ [2024-08-21 21:06:15,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 1826816. Throughput: 0: 903.8. Samples: 454824. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
420
+ [2024-08-21 21:06:15,795][00286] Avg episode reward: [(0, '4.873')]
421
+ [2024-08-21 21:06:19,123][03214] Updated weights for policy 0, policy_version 450 (0.0015)
422
+ [2024-08-21 21:06:20,793][00286] Fps is (10 sec: 4505.7, 60 sec: 3754.8, 300 sec: 3637.8). Total num frames: 1847296. Throughput: 0: 960.4. Samples: 461444. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
423
+ [2024-08-21 21:06:20,799][00286] Avg episode reward: [(0, '4.753')]
424
+ [2024-08-21 21:06:25,794][00286] Fps is (10 sec: 3276.5, 60 sec: 3618.1, 300 sec: 3624.0). Total num frames: 1859584. Throughput: 0: 922.5. Samples: 465842. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
425
+ [2024-08-21 21:06:25,796][00286] Avg episode reward: [(0, '4.769')]
426
+ [2024-08-21 21:06:30,793][00286] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1880064. Throughput: 0: 904.4. Samples: 468396. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
427
+ [2024-08-21 21:06:30,799][00286] Avg episode reward: [(0, '4.800')]
428
+ [2024-08-21 21:06:31,119][03214] Updated weights for policy 0, policy_version 460 (0.0027)
429
+ [2024-08-21 21:06:35,793][00286] Fps is (10 sec: 4506.1, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 1904640. Throughput: 0: 943.2. Samples: 475238. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
430
+ [2024-08-21 21:06:35,794][00286] Avg episode reward: [(0, '4.735')]
431
+ [2024-08-21 21:06:40,797][00286] Fps is (10 sec: 4094.5, 60 sec: 3754.4, 300 sec: 3651.6). Total num frames: 1921024. Throughput: 0: 947.7. Samples: 480628. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
432
+ [2024-08-21 21:06:40,799][00286] Avg episode reward: [(0, '4.923')]
433
+ [2024-08-21 21:06:42,095][03214] Updated weights for policy 0, policy_version 470 (0.0023)
434
+ [2024-08-21 21:06:45,794][00286] Fps is (10 sec: 3276.5, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1937408. Throughput: 0: 918.4. Samples: 482668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
435
+ [2024-08-21 21:06:45,798][00286] Avg episode reward: [(0, '4.811')]
436
+ [2024-08-21 21:06:50,793][00286] Fps is (10 sec: 3687.8, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 1957888. Throughput: 0: 924.8. Samples: 488994. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
437
+ [2024-08-21 21:06:50,795][00286] Avg episode reward: [(0, '4.706')]
438
+ [2024-08-21 21:06:52,030][03214] Updated weights for policy 0, policy_version 480 (0.0037)
439
+ [2024-08-21 21:06:55,793][00286] Fps is (10 sec: 4096.3, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 1978368. Throughput: 0: 976.4. Samples: 495476. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
440
+ [2024-08-21 21:06:55,799][00286] Avg episode reward: [(0, '4.792')]
441
+ [2024-08-21 21:07:00,794][00286] Fps is (10 sec: 3276.5, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 1990656. Throughput: 0: 946.1. Samples: 497400. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
442
+ [2024-08-21 21:07:00,801][00286] Avg episode reward: [(0, '4.774')]
443
+ [2024-08-21 21:07:03,933][03214] Updated weights for policy 0, policy_version 490 (0.0030)
444
+ [2024-08-21 21:07:05,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2011136. Throughput: 0: 918.1. Samples: 502758. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
445
+ [2024-08-21 21:07:05,795][00286] Avg episode reward: [(0, '4.818')]
446
+ [2024-08-21 21:07:10,793][00286] Fps is (10 sec: 4505.9, 60 sec: 3891.2, 300 sec: 3679.5). Total num frames: 2035712. Throughput: 0: 966.8. Samples: 509346. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
447
+ [2024-08-21 21:07:10,798][00286] Avg episode reward: [(0, '4.651')]
448
+ [2024-08-21 21:07:14,204][03214] Updated weights for policy 0, policy_version 500 (0.0036)
449
+ [2024-08-21 21:07:15,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2052096. Throughput: 0: 967.8. Samples: 511948. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
450
+ [2024-08-21 21:07:15,801][00286] Avg episode reward: [(0, '4.586')]
451
+ [2024-08-21 21:07:20,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 2068480. Throughput: 0: 910.4. Samples: 516208. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
452
+ [2024-08-21 21:07:20,795][00286] Avg episode reward: [(0, '4.539')]
453
+ [2024-08-21 21:07:20,804][03197] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000505_2068480.pth...
454
+ [2024-08-21 21:07:20,956][03197] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000289_1183744.pth
455
+ [2024-08-21 21:07:25,146][03214] Updated weights for policy 0, policy_version 510 (0.0053)
456
+ [2024-08-21 21:07:25,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3679.5). Total num frames: 2088960. Throughput: 0: 938.2. Samples: 522842. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
457
+ [2024-08-21 21:07:25,797][00286] Avg episode reward: [(0, '4.581')]
458
+ [2024-08-21 21:07:30,796][00286] Fps is (10 sec: 4094.9, 60 sec: 3822.8, 300 sec: 3679.4). Total num frames: 2109440. Throughput: 0: 970.0. Samples: 526318. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
459
+ [2024-08-21 21:07:30,803][00286] Avg episode reward: [(0, '4.780')]
460
+ [2024-08-21 21:07:35,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 2121728. Throughput: 0: 927.5. Samples: 530732. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
461
+ [2024-08-21 21:07:35,804][00286] Avg episode reward: [(0, '4.717')]
462
+ [2024-08-21 21:07:37,403][03214] Updated weights for policy 0, policy_version 520 (0.0020)
463
+ [2024-08-21 21:07:40,793][00286] Fps is (10 sec: 3277.7, 60 sec: 3686.6, 300 sec: 3679.5). Total num frames: 2142208. Throughput: 0: 909.9. Samples: 536420. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
464
+ [2024-08-21 21:07:40,798][00286] Avg episode reward: [(0, '4.620')]
465
+ [2024-08-21 21:07:45,793][00286] Fps is (10 sec: 4505.5, 60 sec: 3823.0, 300 sec: 3693.3). Total num frames: 2166784. Throughput: 0: 944.9. Samples: 539922. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
466
+ [2024-08-21 21:07:45,796][00286] Avg episode reward: [(0, '4.498')]
467
+ [2024-08-21 21:07:46,300][03214] Updated weights for policy 0, policy_version 530 (0.0035)
468
+ [2024-08-21 21:07:50,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2183168. Throughput: 0: 950.0. Samples: 545510. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
469
+ [2024-08-21 21:07:50,801][00286] Avg episode reward: [(0, '4.733')]
470
+ [2024-08-21 21:07:55,793][00286] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2199552. Throughput: 0: 913.9. Samples: 550470. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
471
+ [2024-08-21 21:07:55,799][00286] Avg episode reward: [(0, '4.575')]
472
+ [2024-08-21 21:07:57,949][03214] Updated weights for policy 0, policy_version 540 (0.0016)
473
+ [2024-08-21 21:08:00,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3891.3, 300 sec: 3721.1). Total num frames: 2224128. Throughput: 0: 933.4. Samples: 553950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
474
+ [2024-08-21 21:08:00,798][00286] Avg episode reward: [(0, '4.449')]
475
+ [2024-08-21 21:08:05,794][00286] Fps is (10 sec: 4095.7, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 2240512. Throughput: 0: 978.5. Samples: 560242. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
476
+ [2024-08-21 21:08:05,796][00286] Avg episode reward: [(0, '4.618')]
477
+ [2024-08-21 21:08:09,677][03214] Updated weights for policy 0, policy_version 550 (0.0031)
478
+ [2024-08-21 21:08:10,795][00286] Fps is (10 sec: 2866.5, 60 sec: 3618.0, 300 sec: 3693.3). Total num frames: 2252800. Throughput: 0: 921.9. Samples: 564330. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
479
+ [2024-08-21 21:08:10,798][00286] Avg episode reward: [(0, '4.726')]
480
+ [2024-08-21 21:08:15,793][00286] Fps is (10 sec: 3686.6, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2277376. Throughput: 0: 909.5. Samples: 567242. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
481
+ [2024-08-21 21:08:15,799][00286] Avg episode reward: [(0, '4.685')]
482
+ [2024-08-21 21:08:19,591][03214] Updated weights for policy 0, policy_version 560 (0.0032)
483
+ [2024-08-21 21:08:20,793][00286] Fps is (10 sec: 4506.7, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 2297856. Throughput: 0: 957.2. Samples: 573808. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
484
+ [2024-08-21 21:08:20,795][00286] Avg episode reward: [(0, '4.646')]
485
+ [2024-08-21 21:08:25,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 2310144. Throughput: 0: 934.6. Samples: 578478. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
486
+ [2024-08-21 21:08:25,799][00286] Avg episode reward: [(0, '4.658')]
487
+ [2024-08-21 21:08:30,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3618.3, 300 sec: 3679.5). Total num frames: 2326528. Throughput: 0: 901.6. Samples: 580496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
488
+ [2024-08-21 21:08:30,796][00286] Avg episode reward: [(0, '4.651')]
489
+ [2024-08-21 21:08:31,724][03214] Updated weights for policy 0, policy_version 570 (0.0021)
490
+ [2024-08-21 21:08:35,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 2351104. Throughput: 0: 922.7. Samples: 587032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
491
+ [2024-08-21 21:08:35,795][00286] Avg episode reward: [(0, '4.745')]
492
+ [2024-08-21 21:08:40,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2367488. Throughput: 0: 940.2. Samples: 592778. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
493
+ [2024-08-21 21:08:40,796][00286] Avg episode reward: [(0, '4.706')]
494
+ [2024-08-21 21:08:42,850][03214] Updated weights for policy 0, policy_version 580 (0.0027)
495
+ [2024-08-21 21:08:45,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 2383872. Throughput: 0: 907.0. Samples: 594766. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
496
+ [2024-08-21 21:08:45,803][00286] Avg episode reward: [(0, '4.489')]
497
+ [2024-08-21 21:08:50,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2404352. Throughput: 0: 893.7. Samples: 600458. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
498
+ [2024-08-21 21:08:50,795][00286] Avg episode reward: [(0, '4.449')]
499
+ [2024-08-21 21:08:53,162][03214] Updated weights for policy 0, policy_version 590 (0.0029)
500
+ [2024-08-21 21:08:55,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 2424832. Throughput: 0: 952.2. Samples: 607176. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
501
+ [2024-08-21 21:08:55,795][00286] Avg episode reward: [(0, '4.431')]
502
+ [2024-08-21 21:09:00,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 2441216. Throughput: 0: 939.9. Samples: 609536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
503
+ [2024-08-21 21:09:00,800][00286] Avg episode reward: [(0, '4.480')]
504
+ [2024-08-21 21:09:04,975][03214] Updated weights for policy 0, policy_version 600 (0.0029)
505
+ [2024-08-21 21:09:05,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3693.3). Total num frames: 2457600. Throughput: 0: 897.4. Samples: 614192. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
506
+ [2024-08-21 21:09:05,802][00286] Avg episode reward: [(0, '4.540')]
507
+ [2024-08-21 21:09:10,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3823.1, 300 sec: 3707.2). Total num frames: 2482176. Throughput: 0: 935.7. Samples: 620586. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
508
+ [2024-08-21 21:09:10,795][00286] Avg episode reward: [(0, '4.610')]
509
+ [2024-08-21 21:09:15,295][03214] Updated weights for policy 0, policy_version 610 (0.0035)
510
+ [2024-08-21 21:09:15,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.4). Total num frames: 2498560. Throughput: 0: 967.1. Samples: 624016. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
511
+ [2024-08-21 21:09:15,796][00286] Avg episode reward: [(0, '4.600')]
512
+ [2024-08-21 21:09:20,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 2510848. Throughput: 0: 908.8. Samples: 627930. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
513
+ [2024-08-21 21:09:20,795][00286] Avg episode reward: [(0, '4.601')]
514
+ [2024-08-21 21:09:20,808][03197] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000613_2510848.pth...
515
+ [2024-08-21 21:09:20,936][03197] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000396_1622016.pth
516
+ [2024-08-21 21:09:25,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2531328. Throughput: 0: 913.4. Samples: 633880. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
517
+ [2024-08-21 21:09:25,797][00286] Avg episode reward: [(0, '4.680')]
518
+ [2024-08-21 21:09:26,813][03214] Updated weights for policy 0, policy_version 620 (0.0027)
519
+ [2024-08-21 21:09:30,793][00286] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 2555904. Throughput: 0: 942.4. Samples: 637172. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
520
+ [2024-08-21 21:09:30,795][00286] Avg episode reward: [(0, '4.894')]
521
+ [2024-08-21 21:09:35,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 2568192. Throughput: 0: 925.6. Samples: 642110. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
522
+ [2024-08-21 21:09:35,795][00286] Avg episode reward: [(0, '4.763')]
523
+ [2024-08-21 21:09:39,152][03214] Updated weights for policy 0, policy_version 630 (0.0018)
524
+ [2024-08-21 21:09:40,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 2584576. Throughput: 0: 884.7. Samples: 646988. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
525
+ [2024-08-21 21:09:40,800][00286] Avg episode reward: [(0, '4.808')]
526
+ [2024-08-21 21:09:45,793][00286] Fps is (10 sec: 4095.9, 60 sec: 3754.6, 300 sec: 3707.2). Total num frames: 2609152. Throughput: 0: 903.5. Samples: 650192. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
527
+ [2024-08-21 21:09:45,798][00286] Avg episode reward: [(0, '4.930')]
528
+ [2024-08-21 21:09:48,756][03214] Updated weights for policy 0, policy_version 640 (0.0022)
529
+ [2024-08-21 21:09:50,793][00286] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3693.4). Total num frames: 2625536. Throughput: 0: 935.4. Samples: 656286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
530
+ [2024-08-21 21:09:50,796][00286] Avg episode reward: [(0, '4.789')]
531
+ [2024-08-21 21:09:55,793][00286] Fps is (10 sec: 2867.3, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 2637824. Throughput: 0: 885.9. Samples: 660450. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
532
+ [2024-08-21 21:09:55,794][00286] Avg episode reward: [(0, '4.819')]
533
+ [2024-08-21 21:10:00,515][03214] Updated weights for policy 0, policy_version 650 (0.0017)
534
+ [2024-08-21 21:10:00,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2662400. Throughput: 0: 881.6. Samples: 663688. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
535
+ [2024-08-21 21:10:00,795][00286] Avg episode reward: [(0, '5.059')]
536
+ [2024-08-21 21:10:00,812][03197] Saving new best policy, reward=5.059!
537
+ [2024-08-21 21:10:05,795][00286] Fps is (10 sec: 4504.8, 60 sec: 3754.6, 300 sec: 3707.2). Total num frames: 2682880. Throughput: 0: 940.6. Samples: 670258. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
538
+ [2024-08-21 21:10:05,799][00286] Avg episode reward: [(0, '4.912')]
539
+ [2024-08-21 21:10:10,797][00286] Fps is (10 sec: 3275.6, 60 sec: 3549.6, 300 sec: 3707.2). Total num frames: 2695168. Throughput: 0: 906.5. Samples: 674678. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
540
+ [2024-08-21 21:10:10,801][00286] Avg episode reward: [(0, '4.945')]
541
+ [2024-08-21 21:10:12,973][03214] Updated weights for policy 0, policy_version 660 (0.0036)
542
+ [2024-08-21 21:10:15,793][00286] Fps is (10 sec: 3277.4, 60 sec: 3618.1, 300 sec: 3707.3). Total num frames: 2715648. Throughput: 0: 883.0. Samples: 676906. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
543
+ [2024-08-21 21:10:15,798][00286] Avg episode reward: [(0, '4.805')]
544
+ [2024-08-21 21:10:20,793][00286] Fps is (10 sec: 4097.4, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2736128. Throughput: 0: 922.4. Samples: 683618. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
545
+ [2024-08-21 21:10:20,795][00286] Avg episode reward: [(0, '4.758')]
546
+ [2024-08-21 21:10:21,931][03214] Updated weights for policy 0, policy_version 670 (0.0026)
547
+ [2024-08-21 21:10:25,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2752512. Throughput: 0: 941.8. Samples: 689368. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
548
+ [2024-08-21 21:10:25,795][00286] Avg episode reward: [(0, '4.566')]
549
+ [2024-08-21 21:10:30,793][00286] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3707.2). Total num frames: 2768896. Throughput: 0: 916.2. Samples: 691422. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
550
+ [2024-08-21 21:10:30,798][00286] Avg episode reward: [(0, '4.422')]
551
+ [2024-08-21 21:10:33,866][03214] Updated weights for policy 0, policy_version 680 (0.0029)
552
+ [2024-08-21 21:10:35,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2793472. Throughput: 0: 915.0. Samples: 697460. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
553
+ [2024-08-21 21:10:35,794][00286] Avg episode reward: [(0, '4.577')]
554
+ [2024-08-21 21:10:40,794][00286] Fps is (10 sec: 4505.1, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 2813952. Throughput: 0: 967.4. Samples: 703982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
555
+ [2024-08-21 21:10:40,801][00286] Avg episode reward: [(0, '4.717')]
556
+ [2024-08-21 21:10:44,755][03214] Updated weights for policy 0, policy_version 690 (0.0027)
557
+ [2024-08-21 21:10:45,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3707.2). Total num frames: 2826240. Throughput: 0: 939.6. Samples: 705968. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
558
+ [2024-08-21 21:10:45,796][00286] Avg episode reward: [(0, '4.850')]
559
+ [2024-08-21 21:10:50,793][00286] Fps is (10 sec: 3277.2, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2846720. Throughput: 0: 901.9. Samples: 710842. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
560
+ [2024-08-21 21:10:50,799][00286] Avg episode reward: [(0, '4.756')]
561
+ [2024-08-21 21:10:55,197][03214] Updated weights for policy 0, policy_version 700 (0.0031)
562
+ [2024-08-21 21:10:55,796][00286] Fps is (10 sec: 4094.9, 60 sec: 3822.8, 300 sec: 3707.2). Total num frames: 2867200. Throughput: 0: 952.4. Samples: 717534. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
563
+ [2024-08-21 21:10:55,798][00286] Avg episode reward: [(0, '4.786')]
564
+ [2024-08-21 21:11:00,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2883584. Throughput: 0: 969.8. Samples: 720548. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
565
+ [2024-08-21 21:11:00,799][00286] Avg episode reward: [(0, '4.701')]
566
+ [2024-08-21 21:11:05,793][00286] Fps is (10 sec: 3277.7, 60 sec: 3618.2, 300 sec: 3721.1). Total num frames: 2899968. Throughput: 0: 913.9. Samples: 724742. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
567
+ [2024-08-21 21:11:05,795][00286] Avg episode reward: [(0, '4.599')]
568
+ [2024-08-21 21:11:07,107][03214] Updated weights for policy 0, policy_version 710 (0.0037)
569
+ [2024-08-21 21:11:10,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3754.9, 300 sec: 3707.2). Total num frames: 2920448. Throughput: 0: 927.6. Samples: 731112. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
570
+ [2024-08-21 21:11:10,807][00286] Avg episode reward: [(0, '4.587')]
571
+ [2024-08-21 21:11:15,793][00286] Fps is (10 sec: 4095.9, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2940928. Throughput: 0: 955.7. Samples: 734428. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
572
+ [2024-08-21 21:11:15,795][00286] Avg episode reward: [(0, '4.558')]
573
+ [2024-08-21 21:11:17,484][03214] Updated weights for policy 0, policy_version 720 (0.0035)
574
+ [2024-08-21 21:11:20,795][00286] Fps is (10 sec: 3685.7, 60 sec: 3686.3, 300 sec: 3721.1). Total num frames: 2957312. Throughput: 0: 925.8. Samples: 739124. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
575
+ [2024-08-21 21:11:20,797][00286] Avg episode reward: [(0, '4.591')]
576
+ [2024-08-21 21:11:20,809][03197] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000722_2957312.pth...
577
+ [2024-08-21 21:11:20,971][03197] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000505_2068480.pth
578
+ [2024-08-21 21:11:25,793][00286] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2973696. Throughput: 0: 897.8. Samples: 744384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
579
+ [2024-08-21 21:11:25,798][00286] Avg episode reward: [(0, '4.473')]
580
+ [2024-08-21 21:11:28,768][03214] Updated weights for policy 0, policy_version 730 (0.0023)
581
+ [2024-08-21 21:11:30,793][00286] Fps is (10 sec: 4096.8, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 2998272. Throughput: 0: 925.9. Samples: 747632. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
582
+ [2024-08-21 21:11:30,797][00286] Avg episode reward: [(0, '4.562')]
583
+ [2024-08-21 21:11:35,797][00286] Fps is (10 sec: 4094.4, 60 sec: 3686.2, 300 sec: 3707.2). Total num frames: 3014656. Throughput: 0: 944.4. Samples: 753342. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
584
+ [2024-08-21 21:11:35,807][00286] Avg episode reward: [(0, '4.714')]
585
+ [2024-08-21 21:11:40,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3693.4). Total num frames: 3026944. Throughput: 0: 891.5. Samples: 757650. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
586
+ [2024-08-21 21:11:40,795][00286] Avg episode reward: [(0, '4.550')]
587
+ [2024-08-21 21:11:40,871][03214] Updated weights for policy 0, policy_version 740 (0.0032)
588
+ [2024-08-21 21:11:45,793][00286] Fps is (10 sec: 3687.8, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 3051520. Throughput: 0: 899.3. Samples: 761018. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
589
+ [2024-08-21 21:11:45,801][00286] Avg episode reward: [(0, '4.371')]
590
+ [2024-08-21 21:11:50,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3067904. Throughput: 0: 947.3. Samples: 767372. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
591
+ [2024-08-21 21:11:50,796][00286] Avg episode reward: [(0, '4.738')]
592
+ [2024-08-21 21:11:50,883][03214] Updated weights for policy 0, policy_version 750 (0.0025)
593
+ [2024-08-21 21:11:55,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3550.0, 300 sec: 3693.4). Total num frames: 3080192. Throughput: 0: 890.7. Samples: 771194. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
594
+ [2024-08-21 21:11:55,799][00286] Avg episode reward: [(0, '4.803')]
595
+ [2024-08-21 21:12:00,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 3104768. Throughput: 0: 879.1. Samples: 773986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
596
+ [2024-08-21 21:12:00,799][00286] Avg episode reward: [(0, '4.572')]
597
+ [2024-08-21 21:12:02,602][03214] Updated weights for policy 0, policy_version 760 (0.0035)
598
+ [2024-08-21 21:12:05,793][00286] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 3125248. Throughput: 0: 925.5. Samples: 780768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
599
+ [2024-08-21 21:12:05,799][00286] Avg episode reward: [(0, '4.720')]
600
+ [2024-08-21 21:12:10,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3141632. Throughput: 0: 918.4. Samples: 785712. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
601
+ [2024-08-21 21:12:10,804][00286] Avg episode reward: [(0, '4.939')]
602
+ [2024-08-21 21:12:14,962][03214] Updated weights for policy 0, policy_version 770 (0.0037)
603
+ [2024-08-21 21:12:15,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 3153920. Throughput: 0: 889.9. Samples: 787678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
604
+ [2024-08-21 21:12:15,798][00286] Avg episode reward: [(0, '4.696')]
605
+ [2024-08-21 21:12:20,793][00286] Fps is (10 sec: 3686.5, 60 sec: 3686.5, 300 sec: 3693.3). Total num frames: 3178496. Throughput: 0: 898.4. Samples: 793768. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
606
+ [2024-08-21 21:12:20,798][00286] Avg episode reward: [(0, '4.615')]
607
+ [2024-08-21 21:12:24,856][03214] Updated weights for policy 0, policy_version 780 (0.0018)
608
+ [2024-08-21 21:12:25,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 3194880. Throughput: 0: 931.6. Samples: 799570. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
609
+ [2024-08-21 21:12:25,801][00286] Avg episode reward: [(0, '4.665')]
610
+ [2024-08-21 21:12:30,796][00286] Fps is (10 sec: 2866.3, 60 sec: 3481.4, 300 sec: 3679.4). Total num frames: 3207168. Throughput: 0: 896.4. Samples: 801358. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
611
+ [2024-08-21 21:12:30,807][00286] Avg episode reward: [(0, '4.655')]
612
+ [2024-08-21 21:12:35,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3679.5). Total num frames: 3227648. Throughput: 0: 864.5. Samples: 806274. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
613
+ [2024-08-21 21:12:35,795][00286] Avg episode reward: [(0, '4.482')]
614
+ [2024-08-21 21:12:37,372][03214] Updated weights for policy 0, policy_version 790 (0.0026)
615
+ [2024-08-21 21:12:40,793][00286] Fps is (10 sec: 4097.3, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3248128. Throughput: 0: 917.4. Samples: 812478. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
616
+ [2024-08-21 21:12:40,795][00286] Avg episode reward: [(0, '4.408')]
617
+ [2024-08-21 21:12:45,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 3260416. Throughput: 0: 910.9. Samples: 814978. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
618
+ [2024-08-21 21:12:45,799][00286] Avg episode reward: [(0, '4.535')]
619
+ [2024-08-21 21:12:49,950][03214] Updated weights for policy 0, policy_version 800 (0.0047)
620
+ [2024-08-21 21:12:50,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 3276800. Throughput: 0: 848.5. Samples: 818952. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
621
+ [2024-08-21 21:12:50,802][00286] Avg episode reward: [(0, '4.750')]
622
+ [2024-08-21 21:12:55,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3301376. Throughput: 0: 881.3. Samples: 825368. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
623
+ [2024-08-21 21:12:55,800][00286] Avg episode reward: [(0, '4.613')]
624
+ [2024-08-21 21:13:00,319][03214] Updated weights for policy 0, policy_version 810 (0.0026)
625
+ [2024-08-21 21:13:00,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 3317760. Throughput: 0: 906.9. Samples: 828488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
626
+ [2024-08-21 21:13:00,800][00286] Avg episode reward: [(0, '4.649')]
627
+ [2024-08-21 21:13:05,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3651.7). Total num frames: 3330048. Throughput: 0: 860.4. Samples: 832488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
628
+ [2024-08-21 21:13:05,799][00286] Avg episode reward: [(0, '4.658')]
629
+ [2024-08-21 21:13:10,793][00286] Fps is (10 sec: 3276.9, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 3350528. Throughput: 0: 853.2. Samples: 837962. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
630
+ [2024-08-21 21:13:10,800][00286] Avg episode reward: [(0, '4.678')]
631
+ [2024-08-21 21:13:12,480][03214] Updated weights for policy 0, policy_version 820 (0.0018)
632
+ [2024-08-21 21:13:15,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3371008. Throughput: 0: 884.1. Samples: 841138. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
633
+ [2024-08-21 21:13:15,799][00286] Avg episode reward: [(0, '4.642')]
634
+ [2024-08-21 21:13:20,793][00286] Fps is (10 sec: 3276.7, 60 sec: 3413.3, 300 sec: 3637.8). Total num frames: 3383296. Throughput: 0: 889.0. Samples: 846280. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
635
+ [2024-08-21 21:13:20,798][00286] Avg episode reward: [(0, '4.712')]
636
+ [2024-08-21 21:13:20,816][03197] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000826_3383296.pth...
637
+ [2024-08-21 21:13:20,999][03197] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000613_2510848.pth
638
+ [2024-08-21 21:13:24,744][03214] Updated weights for policy 0, policy_version 830 (0.0032)
639
+ [2024-08-21 21:13:25,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 3403776. Throughput: 0: 859.2. Samples: 851140. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
640
+ [2024-08-21 21:13:25,804][00286] Avg episode reward: [(0, '5.040')]
641
+ [2024-08-21 21:13:30,793][00286] Fps is (10 sec: 4096.1, 60 sec: 3618.3, 300 sec: 3637.8). Total num frames: 3424256. Throughput: 0: 875.2. Samples: 854364. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
642
+ [2024-08-21 21:13:30,800][00286] Avg episode reward: [(0, '4.984')]
643
+ [2024-08-21 21:13:34,498][03214] Updated weights for policy 0, policy_version 840 (0.0020)
644
+ [2024-08-21 21:13:35,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3440640. Throughput: 0: 925.1. Samples: 860582. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
645
+ [2024-08-21 21:13:35,798][00286] Avg episode reward: [(0, '4.495')]
646
+ [2024-08-21 21:13:40,793][00286] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 3457024. Throughput: 0: 870.1. Samples: 864522. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
647
+ [2024-08-21 21:13:40,797][00286] Avg episode reward: [(0, '4.425')]
648
+ [2024-08-21 21:13:45,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3477504. Throughput: 0: 870.3. Samples: 867652. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
649
+ [2024-08-21 21:13:45,796][00286] Avg episode reward: [(0, '4.404')]
650
+ [2024-08-21 21:13:46,212][03214] Updated weights for policy 0, policy_version 850 (0.0023)
651
+ [2024-08-21 21:13:50,794][00286] Fps is (10 sec: 4505.4, 60 sec: 3754.6, 300 sec: 3651.7). Total num frames: 3502080. Throughput: 0: 930.2. Samples: 874348. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
652
+ [2024-08-21 21:13:50,796][00286] Avg episode reward: [(0, '4.561')]
653
+ [2024-08-21 21:13:55,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3514368. Throughput: 0: 913.1. Samples: 879050. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
654
+ [2024-08-21 21:13:55,795][00286] Avg episode reward: [(0, '4.639')]
655
+ [2024-08-21 21:13:58,297][03214] Updated weights for policy 0, policy_version 860 (0.0015)
656
+ [2024-08-21 21:14:00,793][00286] Fps is (10 sec: 2867.4, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3530752. Throughput: 0: 890.7. Samples: 881220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
657
+ [2024-08-21 21:14:00,799][00286] Avg episode reward: [(0, '4.772')]
658
+ [2024-08-21 21:14:05,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 3555328. Throughput: 0: 926.4. Samples: 887968. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
659
+ [2024-08-21 21:14:05,801][00286] Avg episode reward: [(0, '4.756')]
660
+ [2024-08-21 21:14:07,343][03214] Updated weights for policy 0, policy_version 870 (0.0020)
661
+ [2024-08-21 21:14:10,793][00286] Fps is (10 sec: 4095.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3571712. Throughput: 0: 945.3. Samples: 893680. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
662
+ [2024-08-21 21:14:10,796][00286] Avg episode reward: [(0, '4.483')]
663
+ [2024-08-21 21:14:15,793][00286] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3584000. Throughput: 0: 918.3. Samples: 895688. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
664
+ [2024-08-21 21:14:15,795][00286] Avg episode reward: [(0, '4.528')]
665
+ [2024-08-21 21:14:19,349][03214] Updated weights for policy 0, policy_version 880 (0.0028)
666
+ [2024-08-21 21:14:20,793][00286] Fps is (10 sec: 3686.6, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 3608576. Throughput: 0: 911.7. Samples: 901608. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
667
+ [2024-08-21 21:14:20,795][00286] Avg episode reward: [(0, '4.662')]
668
+ [2024-08-21 21:14:25,793][00286] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 3629056. Throughput: 0: 971.1. Samples: 908222. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
669
+ [2024-08-21 21:14:25,802][00286] Avg episode reward: [(0, '4.628')]
670
+ [2024-08-21 21:14:30,798][00286] Fps is (10 sec: 3275.3, 60 sec: 3617.8, 300 sec: 3637.7). Total num frames: 3641344. Throughput: 0: 945.9. Samples: 910224. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
671
+ [2024-08-21 21:14:30,804][00286] Avg episode reward: [(0, '4.664')]
672
+ [2024-08-21 21:14:30,989][03214] Updated weights for policy 0, policy_version 890 (0.0023)
673
+ [2024-08-21 21:14:35,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3661824. Throughput: 0: 901.5. Samples: 914914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
674
+ [2024-08-21 21:14:35,800][00286] Avg episode reward: [(0, '4.649')]
675
+ [2024-08-21 21:14:40,793][00286] Fps is (10 sec: 4097.9, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 3682304. Throughput: 0: 936.9. Samples: 921212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
676
+ [2024-08-21 21:14:40,795][00286] Avg episode reward: [(0, '4.534')]
677
+ [2024-08-21 21:14:41,179][03214] Updated weights for policy 0, policy_version 900 (0.0024)
678
+ [2024-08-21 21:14:45,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3698688. Throughput: 0: 955.1. Samples: 924200. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
679
+ [2024-08-21 21:14:45,800][00286] Avg episode reward: [(0, '4.441')]
680
+ [2024-08-21 21:14:50,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 3715072. Throughput: 0: 895.2. Samples: 928254. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
681
+ [2024-08-21 21:14:50,795][00286] Avg episode reward: [(0, '4.296')]
682
+ [2024-08-21 21:14:53,311][03214] Updated weights for policy 0, policy_version 910 (0.0033)
683
+ [2024-08-21 21:14:55,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3735552. Throughput: 0: 908.8. Samples: 934576. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
684
+ [2024-08-21 21:14:55,797][00286] Avg episode reward: [(0, '4.250')]
685
+ [2024-08-21 21:15:00,793][00286] Fps is (10 sec: 4095.9, 60 sec: 3754.6, 300 sec: 3637.8). Total num frames: 3756032. Throughput: 0: 939.5. Samples: 937968. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
686
+ [2024-08-21 21:15:00,797][00286] Avg episode reward: [(0, '4.436')]
687
+ [2024-08-21 21:15:04,096][03214] Updated weights for policy 0, policy_version 920 (0.0021)
688
+ [2024-08-21 21:15:05,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3772416. Throughput: 0: 916.1. Samples: 942832. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
689
+ [2024-08-21 21:15:05,797][00286] Avg episode reward: [(0, '4.666')]
690
+ [2024-08-21 21:15:10,793][00286] Fps is (10 sec: 3276.9, 60 sec: 3618.2, 300 sec: 3637.8). Total num frames: 3788800. Throughput: 0: 888.4. Samples: 948202. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
691
+ [2024-08-21 21:15:10,795][00286] Avg episode reward: [(0, '4.793')]
692
+ [2024-08-21 21:15:14,656][03214] Updated weights for policy 0, policy_version 930 (0.0031)
693
+ [2024-08-21 21:15:15,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 3813376. Throughput: 0: 915.7. Samples: 951426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
694
+ [2024-08-21 21:15:15,798][00286] Avg episode reward: [(0, '4.313')]
695
+ [2024-08-21 21:15:20,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3829760. Throughput: 0: 939.6. Samples: 957196. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
696
+ [2024-08-21 21:15:20,797][00286] Avg episode reward: [(0, '4.316')]
697
+ [2024-08-21 21:15:20,808][03197] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000935_3829760.pth...
698
+ [2024-08-21 21:15:20,966][03197] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000722_2957312.pth
699
+ [2024-08-21 21:15:25,793][00286] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3846144. Throughput: 0: 897.9. Samples: 961616. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
700
+ [2024-08-21 21:15:25,798][00286] Avg episode reward: [(0, '4.450')]
701
+ [2024-08-21 21:15:26,661][03214] Updated weights for policy 0, policy_version 940 (0.0034)
702
+ [2024-08-21 21:15:30,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3755.0, 300 sec: 3637.8). Total num frames: 3866624. Throughput: 0: 907.5. Samples: 965036. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
703
+ [2024-08-21 21:15:30,796][00286] Avg episode reward: [(0, '4.609')]
704
+ [2024-08-21 21:15:35,796][00286] Fps is (10 sec: 4094.9, 60 sec: 3754.5, 300 sec: 3637.8). Total num frames: 3887104. Throughput: 0: 966.4. Samples: 971746. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
705
+ [2024-08-21 21:15:35,798][00286] Avg episode reward: [(0, '4.449')]
706
+ [2024-08-21 21:15:36,454][03214] Updated weights for policy 0, policy_version 950 (0.0021)
707
+ [2024-08-21 21:15:40,796][00286] Fps is (10 sec: 3275.9, 60 sec: 3618.0, 300 sec: 3637.8). Total num frames: 3899392. Throughput: 0: 918.8. Samples: 975924. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
708
+ [2024-08-21 21:15:40,798][00286] Avg episode reward: [(0, '4.630')]
709
+ [2024-08-21 21:15:45,793][00286] Fps is (10 sec: 3277.7, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3919872. Throughput: 0: 901.2. Samples: 978520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
710
+ [2024-08-21 21:15:45,795][00286] Avg episode reward: [(0, '4.917')]
711
+ [2024-08-21 21:15:47,792][03214] Updated weights for policy 0, policy_version 960 (0.0026)
712
+ [2024-08-21 21:15:50,793][00286] Fps is (10 sec: 4506.8, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 3944448. Throughput: 0: 942.9. Samples: 985264. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
713
+ [2024-08-21 21:15:50,795][00286] Avg episode reward: [(0, '4.799')]
714
+ [2024-08-21 21:15:55,793][00286] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 3960832. Throughput: 0: 937.7. Samples: 990400. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
715
+ [2024-08-21 21:15:55,795][00286] Avg episode reward: [(0, '4.624')]
716
+ [2024-08-21 21:15:59,788][03214] Updated weights for policy 0, policy_version 970 (0.0030)
717
+ [2024-08-21 21:16:00,793][00286] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3977216. Throughput: 0: 911.4. Samples: 992438. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
718
+ [2024-08-21 21:16:00,803][00286] Avg episode reward: [(0, '4.561')]
719
+ [2024-08-21 21:16:05,793][00286] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 3997696. Throughput: 0: 923.9. Samples: 998770. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
720
+ [2024-08-21 21:16:05,798][00286] Avg episode reward: [(0, '4.624')]
721
+ [2024-08-21 21:16:07,286][03197] Stopping Batcher_0...
722
+ [2024-08-21 21:16:07,286][03197] Loop batcher_evt_loop terminating...
723
+ [2024-08-21 21:16:07,293][03197] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
724
+ [2024-08-21 21:16:07,296][00286] Component Batcher_0 stopped!
725
+ [2024-08-21 21:16:07,341][03214] Weights refcount: 2 0
726
+ [2024-08-21 21:16:07,344][03214] Stopping InferenceWorker_p0-w0...
727
+ [2024-08-21 21:16:07,345][03214] Loop inference_proc0-0_evt_loop terminating...
728
+ [2024-08-21 21:16:07,344][00286] Component InferenceWorker_p0-w0 stopped!
729
+ [2024-08-21 21:16:07,450][03197] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000826_3383296.pth
730
+ [2024-08-21 21:16:07,461][03197] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
731
+ [2024-08-21 21:16:07,702][03197] Stopping LearnerWorker_p0...
732
+ [2024-08-21 21:16:07,707][03197] Loop learner_proc0_evt_loop terminating...
733
+ [2024-08-21 21:16:07,704][03215] Stopping RolloutWorker_w0...
734
+ [2024-08-21 21:16:07,706][00286] Component LearnerWorker_p0 stopped!
735
+ [2024-08-21 21:16:07,711][03215] Loop rollout_proc0_evt_loop terminating...
736
+ [2024-08-21 21:16:07,721][00286] Component RolloutWorker_w0 stopped!
737
+ [2024-08-21 21:16:07,733][00286] Component RolloutWorker_w2 stopped!
738
+ [2024-08-21 21:16:07,737][03216] Stopping RolloutWorker_w2...
739
+ [2024-08-21 21:16:07,740][03216] Loop rollout_proc2_evt_loop terminating...
740
+ [2024-08-21 21:16:07,756][03217] Stopping RolloutWorker_w1...
741
+ [2024-08-21 21:16:07,757][03217] Loop rollout_proc1_evt_loop terminating...
742
+ [2024-08-21 21:16:07,756][00286] Component RolloutWorker_w1 stopped!
743
+ [2024-08-21 21:16:07,774][03219] Stopping RolloutWorker_w5...
744
+ [2024-08-21 21:16:07,774][00286] Component RolloutWorker_w5 stopped!
745
+ [2024-08-21 21:16:07,776][03219] Loop rollout_proc5_evt_loop terminating...
746
+ [2024-08-21 21:16:07,785][00286] Component RolloutWorker_w7 stopped!
747
+ [2024-08-21 21:16:07,788][03221] Stopping RolloutWorker_w7...
748
+ [2024-08-21 21:16:07,794][00286] Component RolloutWorker_w3 stopped!
749
+ [2024-08-21 21:16:07,798][03218] Stopping RolloutWorker_w3...
750
+ [2024-08-21 21:16:07,790][03221] Loop rollout_proc7_evt_loop terminating...
751
+ [2024-08-21 21:16:07,799][03218] Loop rollout_proc3_evt_loop terminating...
752
+ [2024-08-21 21:16:07,810][03222] Stopping RolloutWorker_w6...
753
+ [2024-08-21 21:16:07,810][00286] Component RolloutWorker_w6 stopped!
754
+ [2024-08-21 21:16:07,815][03222] Loop rollout_proc6_evt_loop terminating...
755
+ [2024-08-21 21:16:07,888][03220] Stopping RolloutWorker_w4...
756
+ [2024-08-21 21:16:07,888][00286] Component RolloutWorker_w4 stopped!
757
+ [2024-08-21 21:16:07,892][03220] Loop rollout_proc4_evt_loop terminating...
758
+ [2024-08-21 21:16:07,892][00286] Waiting for process learner_proc0 to stop...
759
+ [2024-08-21 21:16:09,260][00286] Waiting for process inference_proc0-0 to join...
760
+ [2024-08-21 21:16:09,267][00286] Waiting for process rollout_proc0 to join...
761
+ [2024-08-21 21:16:12,192][00286] Waiting for process rollout_proc1 to join...
762
+ [2024-08-21 21:16:12,196][00286] Waiting for process rollout_proc2 to join...
763
+ [2024-08-21 21:16:12,200][00286] Waiting for process rollout_proc3 to join...
764
+ [2024-08-21 21:16:12,205][00286] Waiting for process rollout_proc4 to join...
765
+ [2024-08-21 21:16:12,210][00286] Waiting for process rollout_proc5 to join...
766
+ [2024-08-21 21:16:12,214][00286] Waiting for process rollout_proc6 to join...
767
+ [2024-08-21 21:16:12,220][00286] Waiting for process rollout_proc7 to join...
768
+ [2024-08-21 21:16:12,225][00286] Batcher 0 profile tree view:
769
+ batching: 26.8707, releasing_batches: 0.0289
770
+ [2024-08-21 21:16:12,227][00286] InferenceWorker_p0-w0 profile tree view:
771
+ wait_policy: 0.0000
772
+ wait_policy_total: 423.7363
773
+ update_model: 9.4612
774
+ weight_update: 0.0030
775
+ one_step: 0.0058
776
+ handle_policy_step: 623.2701
777
+ deserialize: 16.6336, stack: 3.2684, obs_to_device_normalize: 125.7079, forward: 333.4557, send_messages: 30.2082
778
+ prepare_outputs: 83.4280
779
+ to_cpu: 47.9837
780
+ [2024-08-21 21:16:12,230][00286] Learner 0 profile tree view:
781
+ misc: 0.0052, prepare_batch: 14.6260
782
+ train: 75.3809
783
+ epoch_init: 0.0133, minibatch_init: 0.0111, losses_postprocess: 0.6441, kl_divergence: 0.6862, after_optimizer: 34.4669
784
+ calculate_losses: 27.4056
785
+ losses_init: 0.0136, forward_head: 1.3108, bptt_initial: 17.9403, tail: 1.1918, advantages_returns: 0.2754, losses: 3.9182
786
+ bptt: 2.3882
787
+ bptt_forward_core: 2.2559
788
+ update: 11.4269
789
+ clip: 0.9519
790
+ [2024-08-21 21:16:12,234][00286] RolloutWorker_w0 profile tree view:
791
+ wait_for_trajectories: 0.3563, enqueue_policy_requests: 104.1912, env_step: 857.6223, overhead: 14.4259, complete_rollouts: 6.8248
792
+ save_policy_outputs: 22.5305
793
+ split_output_tensors: 9.1667
794
+ [2024-08-21 21:16:12,236][00286] RolloutWorker_w7 profile tree view:
795
+ wait_for_trajectories: 0.3231, enqueue_policy_requests: 105.1923, env_step: 850.3135, overhead: 14.6101, complete_rollouts: 7.4775
796
+ save_policy_outputs: 22.1450
797
+ split_output_tensors: 8.8024
798
+ [2024-08-21 21:16:12,237][00286] Loop Runner_EvtLoop terminating...
799
+ [2024-08-21 21:16:12,239][00286] Runner profile tree view:
800
+ main_loop: 1127.0205
801
+ [2024-08-21 21:16:12,242][00286] Collected {0: 4005888}, FPS: 3554.4
802
+ [2024-08-21 21:16:12,276][00286] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
803
+ [2024-08-21 21:16:12,278][00286] Overriding arg 'num_workers' with value 1 passed from command line
804
+ [2024-08-21 21:16:12,280][00286] Adding new argument 'no_render'=True that is not in the saved config file!
805
+ [2024-08-21 21:16:12,281][00286] Adding new argument 'save_video'=True that is not in the saved config file!
806
+ [2024-08-21 21:16:12,283][00286] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
807
+ [2024-08-21 21:16:12,285][00286] Adding new argument 'video_name'=None that is not in the saved config file!
808
+ [2024-08-21 21:16:12,287][00286] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
809
+ [2024-08-21 21:16:12,288][00286] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
810
+ [2024-08-21 21:16:12,290][00286] Adding new argument 'push_to_hub'=False that is not in the saved config file!
811
+ [2024-08-21 21:16:12,291][00286] Adding new argument 'hf_repository'=None that is not in the saved config file!
812
+ [2024-08-21 21:16:12,294][00286] Adding new argument 'policy_index'=0 that is not in the saved config file!
813
+ [2024-08-21 21:16:12,295][00286] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
814
+ [2024-08-21 21:16:12,296][00286] Adding new argument 'train_script'=None that is not in the saved config file!
815
+ [2024-08-21 21:16:12,298][00286] Adding new argument 'enjoy_script'=None that is not in the saved config file!
816
+ [2024-08-21 21:16:12,300][00286] Using frameskip 1 and render_action_repeat=4 for evaluation
817
+ [2024-08-21 21:16:12,354][00286] Doom resolution: 160x120, resize resolution: (128, 72)
818
+ [2024-08-21 21:16:12,360][00286] RunningMeanStd input shape: (3, 72, 128)
819
+ [2024-08-21 21:16:12,362][00286] RunningMeanStd input shape: (1,)
820
+ [2024-08-21 21:16:12,392][00286] ConvEncoder: input_channels=3
821
+ [2024-08-21 21:16:12,579][00286] Conv encoder output size: 512
822
+ [2024-08-21 21:16:12,581][00286] Policy head output size: 512
823
+ [2024-08-21 21:16:12,815][00286] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
824
+ [2024-08-21 21:16:13,622][00286] Num frames 100...
825
+ [2024-08-21 21:16:13,749][00286] Num frames 200...
826
+ [2024-08-21 21:16:13,873][00286] Num frames 300...
827
+ [2024-08-21 21:16:14,038][00286] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
828
+ [2024-08-21 21:16:14,040][00286] Avg episode reward: 3.840, avg true_objective: 3.840
829
+ [2024-08-21 21:16:14,064][00286] Num frames 400...
830
+ [2024-08-21 21:16:14,188][00286] Num frames 500...
831
+ [2024-08-21 21:16:14,316][00286] Num frames 600...
832
+ [2024-08-21 21:16:14,446][00286] Num frames 700...
833
+ [2024-08-21 21:16:14,583][00286] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
834
+ [2024-08-21 21:16:14,585][00286] Avg episode reward: 3.840, avg true_objective: 3.840
835
+ [2024-08-21 21:16:14,634][00286] Num frames 800...
836
+ [2024-08-21 21:16:14,760][00286] Num frames 900...
837
+ [2024-08-21 21:16:14,895][00286] Num frames 1000...
838
+ [2024-08-21 21:16:15,030][00286] Num frames 1100...
839
+ [2024-08-21 21:16:15,151][00286] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
840
+ [2024-08-21 21:16:15,152][00286] Avg episode reward: 3.840, avg true_objective: 3.840
841
+ [2024-08-21 21:16:15,215][00286] Num frames 1200...
842
+ [2024-08-21 21:16:15,343][00286] Num frames 1300...
843
+ [2024-08-21 21:16:15,470][00286] Num frames 1400...
844
+ [2024-08-21 21:16:15,598][00286] Num frames 1500...
845
+ [2024-08-21 21:16:15,699][00286] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
846
+ [2024-08-21 21:16:15,700][00286] Avg episode reward: 3.840, avg true_objective: 3.840
847
+ [2024-08-21 21:16:15,783][00286] Num frames 1600...
848
+ [2024-08-21 21:16:15,905][00286] Num frames 1700...
849
+ [2024-08-21 21:16:16,032][00286] Num frames 1800...
850
+ [2024-08-21 21:16:16,156][00286] Num frames 1900...
851
+ [2024-08-21 21:16:16,235][00286] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
852
+ [2024-08-21 21:16:16,237][00286] Avg episode reward: 3.840, avg true_objective: 3.840
853
+ [2024-08-21 21:16:16,338][00286] Num frames 2000...
854
+ [2024-08-21 21:16:16,468][00286] Num frames 2100...
855
+ [2024-08-21 21:16:16,589][00286] Num frames 2200...
856
+ [2024-08-21 21:16:16,713][00286] Num frames 2300...
857
+ [2024-08-21 21:16:16,837][00286] Num frames 2400...
858
+ [2024-08-21 21:16:16,935][00286] Avg episode rewards: #0: 4.387, true rewards: #0: 4.053
859
+ [2024-08-21 21:16:16,938][00286] Avg episode reward: 4.387, avg true_objective: 4.053
860
+ [2024-08-21 21:16:17,031][00286] Num frames 2500...
861
+ [2024-08-21 21:16:17,155][00286] Num frames 2600...
862
+ [2024-08-21 21:16:17,279][00286] Num frames 2700...
863
+ [2024-08-21 21:16:17,413][00286] Num frames 2800...
864
+ [2024-08-21 21:16:17,536][00286] Num frames 2900...
865
+ [2024-08-21 21:16:17,661][00286] Num frames 3000...
866
+ [2024-08-21 21:16:17,766][00286] Avg episode rewards: #0: 5.057, true rewards: #0: 4.343
867
+ [2024-08-21 21:16:17,768][00286] Avg episode reward: 5.057, avg true_objective: 4.343
868
+ [2024-08-21 21:16:17,840][00286] Num frames 3100...
869
+ [2024-08-21 21:16:17,961][00286] Num frames 3200...
870
+ [2024-08-21 21:16:18,090][00286] Num frames 3300...
871
+ [2024-08-21 21:16:18,211][00286] Num frames 3400...
872
+ [2024-08-21 21:16:18,368][00286] Avg episode rewards: #0: 5.110, true rewards: #0: 4.360
873
+ [2024-08-21 21:16:18,370][00286] Avg episode reward: 5.110, avg true_objective: 4.360
874
+ [2024-08-21 21:16:18,387][00286] Num frames 3500...
875
+ [2024-08-21 21:16:18,512][00286] Num frames 3600...
876
+ [2024-08-21 21:16:18,632][00286] Num frames 3700...
877
+ [2024-08-21 21:16:18,753][00286] Num frames 3800...
878
+ [2024-08-21 21:16:18,879][00286] Num frames 3900...
879
+ [2024-08-21 21:16:18,978][00286] Avg episode rewards: #0: 5.151, true rewards: #0: 4.373
880
+ [2024-08-21 21:16:18,980][00286] Avg episode reward: 5.151, avg true_objective: 4.373
881
+ [2024-08-21 21:16:19,065][00286] Num frames 4000...
882
+ [2024-08-21 21:16:19,187][00286] Num frames 4100...
883
+ [2024-08-21 21:16:19,307][00286] Num frames 4200...
884
+ [2024-08-21 21:16:19,441][00286] Num frames 4300...
885
+ [2024-08-21 21:16:19,521][00286] Avg episode rewards: #0: 5.020, true rewards: #0: 4.320
886
+ [2024-08-21 21:16:19,523][00286] Avg episode reward: 5.020, avg true_objective: 4.320
887
+ [2024-08-21 21:16:40,466][00286] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
888
+ [2024-08-21 21:16:40,499][00286] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
889
+ [2024-08-21 21:16:40,500][00286] Overriding arg 'num_workers' with value 1 passed from command line
890
+ [2024-08-21 21:16:40,502][00286] Adding new argument 'no_render'=True that is not in the saved config file!
891
+ [2024-08-21 21:16:40,503][00286] Adding new argument 'save_video'=True that is not in the saved config file!
892
+ [2024-08-21 21:16:40,505][00286] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
893
+ [2024-08-21 21:16:40,506][00286] Adding new argument 'video_name'=None that is not in the saved config file!
894
+ [2024-08-21 21:16:40,508][00286] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
895
+ [2024-08-21 21:16:40,509][00286] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
896
+ [2024-08-21 21:16:40,516][00286] Adding new argument 'push_to_hub'=True that is not in the saved config file!
897
+ [2024-08-21 21:16:40,517][00286] Adding new argument 'hf_repository'='fortminors/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
898
+ [2024-08-21 21:16:40,518][00286] Adding new argument 'policy_index'=0 that is not in the saved config file!
899
+ [2024-08-21 21:16:40,519][00286] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
900
+ [2024-08-21 21:16:40,520][00286] Adding new argument 'train_script'=None that is not in the saved config file!
901
+ [2024-08-21 21:16:40,521][00286] Adding new argument 'enjoy_script'=None that is not in the saved config file!
902
+ [2024-08-21 21:16:40,522][00286] Using frameskip 1 and render_action_repeat=4 for evaluation
903
+ [2024-08-21 21:16:40,550][00286] RunningMeanStd input shape: (3, 72, 128)
904
+ [2024-08-21 21:16:40,552][00286] RunningMeanStd input shape: (1,)
905
+ [2024-08-21 21:16:40,565][00286] ConvEncoder: input_channels=3
906
+ [2024-08-21 21:16:40,600][00286] Conv encoder output size: 512
907
+ [2024-08-21 21:16:40,602][00286] Policy head output size: 512
908
+ [2024-08-21 21:16:40,622][00286] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
909
+ [2024-08-21 21:16:41,038][00286] Num frames 100...
910
+ [2024-08-21 21:16:41,160][00286] Num frames 200...
911
+ [2024-08-21 21:16:41,281][00286] Num frames 300...
912
+ [2024-08-21 21:16:41,460][00286] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
913
+ [2024-08-21 21:16:41,462][00286] Avg episode reward: 3.840, avg true_objective: 3.840
914
+ [2024-08-21 21:16:41,492][00286] Num frames 400...
915
+ [2024-08-21 21:16:41,637][00286] Num frames 500...
916
+ [2024-08-21 21:16:41,757][00286] Num frames 600...
917
+ [2024-08-21 21:16:41,886][00286] Num frames 700...
918
+ [2024-08-21 21:16:42,024][00286] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
919
+ [2024-08-21 21:16:42,025][00286] Avg episode reward: 3.840, avg true_objective: 3.840
920
+ [2024-08-21 21:16:42,068][00286] Num frames 800...
921
+ [2024-08-21 21:16:42,187][00286] Num frames 900...
922
+ [2024-08-21 21:16:42,311][00286] Num frames 1000...
923
+ [2024-08-21 21:16:42,443][00286] Num frames 1100...
924
+ [2024-08-21 21:16:42,564][00286] Num frames 1200...
925
+ [2024-08-21 21:16:42,713][00286] Avg episode rewards: #0: 4.933, true rewards: #0: 4.267
926
+ [2024-08-21 21:16:42,714][00286] Avg episode reward: 4.933, avg true_objective: 4.267
927
+ [2024-08-21 21:16:42,743][00286] Num frames 1300...
928
+ [2024-08-21 21:16:42,868][00286] Num frames 1400...
929
+ [2024-08-21 21:16:42,999][00286] Num frames 1500...
930
+ [2024-08-21 21:16:43,121][00286] Num frames 1600...
931
+ [2024-08-21 21:16:43,253][00286] Avg episode rewards: #0: 4.660, true rewards: #0: 4.160
932
+ [2024-08-21 21:16:43,255][00286] Avg episode reward: 4.660, avg true_objective: 4.160
933
+ [2024-08-21 21:16:43,307][00286] Num frames 1700...
934
+ [2024-08-21 21:16:43,434][00286] Num frames 1800...
935
+ [2024-08-21 21:16:43,552][00286] Num frames 1900...
936
+ [2024-08-21 21:16:43,670][00286] Num frames 2000...
937
+ [2024-08-21 21:16:43,782][00286] Avg episode rewards: #0: 4.496, true rewards: #0: 4.096
938
+ [2024-08-21 21:16:43,784][00286] Avg episode reward: 4.496, avg true_objective: 4.096
939
+ [2024-08-21 21:16:43,846][00286] Num frames 2100...
940
+ [2024-08-21 21:16:43,975][00286] Num frames 2200...
941
+ [2024-08-21 21:16:44,093][00286] Num frames 2300...
942
+ [2024-08-21 21:16:44,209][00286] Num frames 2400...
943
+ [2024-08-21 21:16:44,384][00286] Avg episode rewards: #0: 4.660, true rewards: #0: 4.160
944
+ [2024-08-21 21:16:44,385][00286] Avg episode reward: 4.660, avg true_objective: 4.160
945
+ [2024-08-21 21:16:44,395][00286] Num frames 2500...
946
+ [2024-08-21 21:16:44,513][00286] Num frames 2600...
947
+ [2024-08-21 21:16:44,638][00286] Num frames 2700...
948
+ [2024-08-21 21:16:44,758][00286] Num frames 2800...
949
+ [2024-08-21 21:16:44,880][00286] Num frames 2900...
950
+ [2024-08-21 21:16:44,952][00286] Avg episode rewards: #0: 4.874, true rewards: #0: 4.160
951
+ [2024-08-21 21:16:44,954][00286] Avg episode reward: 4.874, avg true_objective: 4.160
952
+ [2024-08-21 21:16:45,062][00286] Num frames 3000...
953
+ [2024-08-21 21:16:45,184][00286] Num frames 3100...
954
+ [2024-08-21 21:16:45,311][00286] Num frames 3200...
955
+ [2024-08-21 21:16:45,489][00286] Avg episode rewards: #0: 4.745, true rewards: #0: 4.120
956
+ [2024-08-21 21:16:45,491][00286] Avg episode reward: 4.745, avg true_objective: 4.120
957
+ [2024-08-21 21:16:45,501][00286] Num frames 3300...
958
+ [2024-08-21 21:16:45,621][00286] Num frames 3400...
959
+ [2024-08-21 21:16:45,743][00286] Num frames 3500...
960
+ [2024-08-21 21:16:45,863][00286] Avg episode rewards: #0: 4.502, true rewards: #0: 3.947
961
+ [2024-08-21 21:16:45,866][00286] Avg episode reward: 4.502, avg true_objective: 3.947
962
+ [2024-08-21 21:16:45,924][00286] Num frames 3600...
963
+ [2024-08-21 21:16:46,053][00286] Num frames 3700...
964
+ [2024-08-21 21:16:46,177][00286] Num frames 3800...
965
+ [2024-08-21 21:16:46,294][00286] Num frames 3900...
966
+ [2024-08-21 21:16:46,427][00286] Num frames 4000...
967
+ [2024-08-21 21:16:46,558][00286] Avg episode rewards: #0: 4.764, true rewards: #0: 4.064
968
+ [2024-08-21 21:16:46,560][00286] Avg episode reward: 4.764, avg true_objective: 4.064
969
+ [2024-08-21 21:17:06,444][00286] Replay video saved to /content/train_dir/default_experiment/replay.mp4!