ernestum commited on
Commit
17178e2
1 Parent(s): d9b7d6d

Initial commit

Browse files
.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
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - seals/HalfCheetah-v1
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: SAC
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: seals/HalfCheetah-v1
16
+ type: seals/HalfCheetah-v1
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 1183.52 +/- 22.65
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **SAC** Agent playing **seals/HalfCheetah-v1**
25
+ This is a trained model of a **SAC** agent playing **seals/HalfCheetah-v1**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
27
+ and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
28
+
29
+ The RL Zoo is a training framework for Stable Baselines3
30
+ reinforcement learning agents,
31
+ with hyperparameter optimization and pre-trained agents included.
32
+
33
+ ## Usage (with SB3 RL Zoo)
34
+
35
+ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
36
+ SB3: https://github.com/DLR-RM/stable-baselines3<br/>
37
+ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
38
+
39
+ Install the RL Zoo (with SB3 and SB3-Contrib):
40
+ ```bash
41
+ pip install rl_zoo3
42
+ ```
43
+
44
+ ```
45
+ # Download model and save it into the logs/ folder
46
+ python -m rl_zoo3.load_from_hub --algo sac --env seals/HalfCheetah-v1 -orga HumanCompatibleAI -f logs/
47
+ python -m rl_zoo3.enjoy --algo sac --env seals/HalfCheetah-v1 -f logs/
48
+ ```
49
+
50
+ If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
51
+ ```
52
+ python -m rl_zoo3.load_from_hub --algo sac --env seals/HalfCheetah-v1 -orga HumanCompatibleAI -f logs/
53
+ python -m rl_zoo3.enjoy --algo sac --env seals/HalfCheetah-v1 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo sac --env seals/HalfCheetah-v1 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo sac --env seals/HalfCheetah-v1 -f logs/ -orga HumanCompatibleAI
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 2048),
66
+ ('buffer_size', 100000),
67
+ ('gamma', 0.95),
68
+ ('learning_rate', 0.000884624878315995),
69
+ ('learning_starts', 10000),
70
+ ('n_timesteps', 1000000.0),
71
+ ('policy', 'MlpPolicy'),
72
+ ('policy_kwargs',
73
+ {'log_std_init': -0.6932709443503001,
74
+ 'net_arch': [64, 64],
75
+ 'use_sde': False}),
76
+ ('tau', 0.01),
77
+ ('train_freq', 64),
78
+ ('normalize', False)])
79
+ ```
80
+
81
+ # Environment Arguments
82
+ ```python
83
+ {'render_mode': 'rgb_array'}
84
+ ```
args.yml ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - sac
4
+ - - conf_file
5
+ - hyperparams/python/sac.py
6
+ - - device
7
+ - cpu
8
+ - - env
9
+ - seals/HalfCheetah-v1
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 0
14
+ - - eval_freq
15
+ - 25000
16
+ - - gym_packages
17
+ - - seals
18
+ - - hyperparams
19
+ - null
20
+ - - log_folder
21
+ - gymnasium_models
22
+ - - log_interval
23
+ - -1
24
+ - - max_total_trials
25
+ - null
26
+ - - n_eval_envs
27
+ - 1
28
+ - - n_evaluations
29
+ - null
30
+ - - n_jobs
31
+ - 1
32
+ - - n_startup_trials
33
+ - 10
34
+ - - n_timesteps
35
+ - -1
36
+ - - n_trials
37
+ - 500
38
+ - - no_optim_plots
39
+ - false
40
+ - - num_threads
41
+ - 4
42
+ - - optimization_log_path
43
+ - null
44
+ - - optimize_hyperparameters
45
+ - false
46
+ - - progress
47
+ - false
48
+ - - pruner
49
+ - median
50
+ - - sampler
51
+ - tpe
52
+ - - save_freq
53
+ - -1
54
+ - - save_replay_buffer
55
+ - false
56
+ - - seed
57
+ - 2958364144
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - ''
64
+ - - track
65
+ - false
66
+ - - trained_agent
67
+ - ''
68
+ - - truncate_last_trajectory
69
+ - true
70
+ - - uuid
71
+ - false
72
+ - - vec_env
73
+ - dummy
74
+ - - verbose
75
+ - 1
76
+ - - wandb_entity
77
+ - null
78
+ - - wandb_project_name
79
+ - sb3
80
+ - - wandb_tags
81
+ - []
config.yml ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 2048
4
+ - - buffer_size
5
+ - 100000
6
+ - - gamma
7
+ - 0.95
8
+ - - learning_rate
9
+ - 0.000884624878315995
10
+ - - learning_starts
11
+ - 10000
12
+ - - n_timesteps
13
+ - 1000000.0
14
+ - - policy
15
+ - MlpPolicy
16
+ - - policy_kwargs
17
+ - log_std_init: -0.6932709443503001
18
+ net_arch:
19
+ - 64
20
+ - 64
21
+ use_sde: false
22
+ - - tau
23
+ - 0.01
24
+ - - train_freq
25
+ - 64
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ render_mode: rgb_array
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d977c437d6d6482691926d4170d09b1b96c6f5321d06e5a29e7170de8411f3
3
+ size 2427924
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 1183.5162696, "std_reward": 22.649349480775626, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T11:52:51.514375"}
sac-seals-HalfCheetah-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4532b2991f27daee4738c580c0e9a8ea69453b144fdeb7b3351c0865fac93dd4
3
+ size 305704
sac-seals-HalfCheetah-v1/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.2.0a3
sac-seals-HalfCheetah-v1/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3098a35c186fec615721ef063e017aa78acdfd2c70e1c3846140100aa2351e90
3
+ size 55453
sac-seals-HalfCheetah-v1/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789843bffdbb6f5d2170d344cb3ad732d4f9921699b06bdbfb0a684d9d07fae6
3
+ size 102329
sac-seals-HalfCheetah-v1/data ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
5
+ "__module__": "stable_baselines3.sac.policies",
6
+ "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}",
7
+ "__doc__": "\n Policy class (with both actor and critic) for SAC.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
8
+ "__init__": "<function SACPolicy.__init__ at 0x7ff313e89700>",
9
+ "_build": "<function SACPolicy._build at 0x7ff313e89790>",
10
+ "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7ff313e89820>",
11
+ "reset_noise": "<function SACPolicy.reset_noise at 0x7ff313e898b0>",
12
+ "make_actor": "<function SACPolicy.make_actor at 0x7ff313e89940>",
13
+ "make_critic": "<function SACPolicy.make_critic at 0x7ff313e899d0>",
14
+ "forward": "<function SACPolicy.forward at 0x7ff313e89a60>",
15
+ "_predict": "<function SACPolicy._predict at 0x7ff313e89af0>",
16
+ "set_training_mode": "<function SACPolicy.set_training_mode at 0x7ff313e89b80>",
17
+ "__abstractmethods__": "frozenset()",
18
+ "_abc_impl": "<_abc_data object at 0x7ff313e80b40>"
19
+ },
20
+ "verbose": 1,
21
+ "policy_kwargs": {
22
+ "net_arch": [
23
+ 64,
24
+ 64
25
+ ],
26
+ "log_std_init": -0.6932709443503001,
27
+ "use_sde": false
28
+ },
29
+ "num_timesteps": 1000000,
30
+ "_total_timesteps": 1000000,
31
+ "_num_timesteps_at_start": 0,
32
+ "seed": 0,
33
+ "action_noise": null,
34
+ "start_time": 1694771152497198306,
35
+ "learning_rate": {
36
+ ":type:": "<class 'function'>",
37
+ ":serialized:": "gAWVlwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZS9ob21lL21heGltaWxpYW4vcmwtYmFzZWxpbmVzMy16b28vdmVudi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLg0MCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHn2UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP0z8xXX21K+FlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
38
+ },
39
+ "tensorboard_log": null,
40
+ "_last_obs": null,
41
+ "_last_episode_starts": {
42
+ ":type:": "<class 'numpy.ndarray'>",
43
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
44
+ },
45
+ "_last_original_obs": {
46
+ ":type:": "<class 'numpy.ndarray'>",
47
+ ":serialized:": "gAWVBQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaQAAAAAAAAAArbnzHbxFJA7/V3QWPb3L9mOu9+IQMMQIon2RFVBeG/ySGl81MI5b8iH4g7bw/SP1ynJSlQw8I/5VlgdExc3T+UlV5h2GHRPwZyEkVM2PQ/8whm69pbyz9YLvYXASj0v2mr/OJJ7eE/+GLJfltS5b/e2lOclzQbwAlSG11CRB3AECktt6c4B0ApBR/0NTgTwJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsShpSMAUOUdJRSlC4="
48
+ },
49
+ "_episode_num": 1000,
50
+ "use_sde": false,
51
+ "sde_sample_freq": -1,
52
+ "_current_progress_remaining": 0.0,
53
+ "_stats_window_size": 100,
54
+ "ep_info_buffer": {
55
+ ":type:": "<class 'collections.deque'>",
56
+ ":serialized:": "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"
57
+ },
58
+ "ep_success_buffer": {
59
+ ":type:": "<class 'collections.deque'>",
60
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
61
+ },
62
+ "_n_updates": 15469,
63
+ "observation_space": {
64
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
65
+ ":serialized:": "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",
66
+ "dtype": "float64",
67
+ "bounded_below": "[False False False False False False False False False False False False\n False False False False False False]",
68
+ "bounded_above": "[False False False False False False False False False False False False\n False False False False False False]",
69
+ "_shape": [
70
+ 18
71
+ ],
72
+ "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf]",
73
+ "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf]",
74
+ "low_repr": "-inf",
75
+ "high_repr": "inf",
76
+ "_np_random": null
77
+ },
78
+ "action_space": {
79
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
80
+ ":serialized:": "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",
81
+ "dtype": "float32",
82
+ "bounded_below": "[ True True True True True True]",
83
+ "bounded_above": "[ True True True True True True]",
84
+ "_shape": [
85
+ 6
86
+ ],
87
+ "low": "[-1. -1. -1. -1. -1. -1.]",
88
+ "high": "[1. 1. 1. 1. 1. 1.]",
89
+ "low_repr": "-1.0",
90
+ "high_repr": "1.0",
91
+ "_np_random": "Generator(PCG64)"
92
+ },
93
+ "n_envs": 1,
94
+ "buffer_size": 1,
95
+ "batch_size": 2048,
96
+ "learning_starts": 10000,
97
+ "tau": 0.01,
98
+ "gamma": 0.95,
99
+ "gradient_steps": 1,
100
+ "optimize_memory_usage": false,
101
+ "replay_buffer_class": {
102
+ ":type:": "<class 'abc.ABCMeta'>",
103
+ ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
104
+ "__module__": "stable_baselines3.common.buffers",
105
+ "__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n Cannot be used in combination with handle_timeout_termination.\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
106
+ "__init__": "<function ReplayBuffer.__init__ at 0x7ff313ed7700>",
107
+ "add": "<function ReplayBuffer.add at 0x7ff313ed7790>",
108
+ "sample": "<function ReplayBuffer.sample at 0x7ff313ed7820>",
109
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x7ff313ed78b0>",
110
+ "_maybe_cast_dtype": "<staticmethod object at 0x7ff313ed0850>",
111
+ "__abstractmethods__": "frozenset()",
112
+ "_abc_impl": "<_abc_data object at 0x7ff313ed0870>"
113
+ },
114
+ "replay_buffer_kwargs": {},
115
+ "train_freq": {
116
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
117
+ ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
118
+ },
119
+ "use_sde_at_warmup": false,
120
+ "target_entropy": -6.0,
121
+ "ent_coef": "auto",
122
+ "target_update_interval": 1,
123
+ "lr_schedule": {
124
+ ":type:": "<class 'function'>",
125
+ ":serialized:": "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"
126
+ },
127
+ "batch_norm_stats": [],
128
+ "batch_norm_stats_target": []
129
+ }
sac-seals-HalfCheetah-v1/ent_coef_optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b6e2491976823ed5614ebbe99fc5bac520cd032e37f6fa8c689af1fa34a5df
3
+ size 1507
sac-seals-HalfCheetah-v1/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62d61ccfb530d7d0f7c5b041c05dbb97d2ad871d8949dfa6bb10aeb2ac5878dc
3
+ size 128261
sac-seals-HalfCheetah-v1/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbdbacbd3325e414982ffd4d836a76db7baf1abde4778bc1ff76ad0c66eb925
3
+ size 747
sac-seals-HalfCheetah-v1/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
2
+ - Python: 3.8.10
3
+ - Stable-Baselines3: 2.2.0a3
4
+ - PyTorch: 2.0.1+cu117
5
+ - GPU Enabled: False
6
+ - Numpy: 1.24.4
7
+ - Cloudpickle: 2.2.1
8
+ - Gymnasium: 0.29.1
9
+ - OpenAI Gym: 0.21.0
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be506b28850193dd6638a80f4c095c21b27d667a226cd16e87193ec97bbf5238
3
+ size 29294