Update to new sim
Browse files- README.md +5 -9
- args.yml +16 -11
- config.yml +3 -1
- env_kwargs.yml +2 -1
- replay.mp4 +2 -2
- results.json +1 -1
- tqc-donkey-mountain-track-v0.zip +2 -2
- tqc-donkey-mountain-track-v0/actor.optimizer.pth +2 -2
- tqc-donkey-mountain-track-v0/critic.optimizer.pth +2 -2
- tqc-donkey-mountain-track-v0/data +25 -25
- tqc-donkey-mountain-track-v0/ent_coef_optimizer.pth +2 -2
- tqc-donkey-mountain-track-v0/policy.pth +2 -2
- tqc-donkey-mountain-track-v0/pytorch_variables.pth +1 -1
- tqc-donkey-mountain-track-v0/system_info.txt +5 -5
- train_eval_metrics.zip +2 -2
- vec_normalize.pkl +1 -1
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value:
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
@@ -35,12 +35,6 @@ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
|
35 |
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
36 |
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
37 |
|
38 |
-
Autoencoder: https://github.com/araffin/aae-train-donkeycar branch: `feat/race_june` <br/>
|
39 |
-
Gym env: https://github.com/araffin/gym-donkeycar-1 branch: `feat/race_june` <br/>
|
40 |
-
RL Zoo branch: `feat/gym-donkeycar`
|
41 |
-
|
42 |
-
**Pretrained autoencoder** can be downloaded here: https://github.com/araffin/aae-train-donkeycar/releases/download/live-twitch-2/ae-32_mountain.pkl
|
43 |
-
|
44 |
```
|
45 |
# Download model and save it into the logs/ folder
|
46 |
python -m utils.load_from_hub --algo tqc --env donkey-mountain-track-v0 -orga araffin -f logs/
|
@@ -63,7 +57,8 @@ OrderedDict([('batch_size', 256),
|
|
63 |
'utils.callbacks.LapTimeCallback']),
|
64 |
('ent_coef', 'auto'),
|
65 |
('env_wrapper',
|
66 |
-
['
|
|
|
67 |
{'utils.wrappers.HistoryWrapper': {'horizon': 2}}]),
|
68 |
('gamma', 0.99),
|
69 |
('gradient_steps', 256),
|
@@ -97,5 +92,6 @@ OrderedDict([('batch_size', 256),
|
|
97 |
'max_cte': 16,
|
98 |
'port': 9091,
|
99 |
'start_delay': 5.0},
|
100 |
-
'
|
|
|
101 |
```
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 363.88 +/- 0.94
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
35 |
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
36 |
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
```
|
39 |
# Download model and save it into the logs/ folder
|
40 |
python -m utils.load_from_hub --algo tqc --env donkey-mountain-track-v0 -orga araffin -f logs/
|
|
|
57 |
'utils.callbacks.LapTimeCallback']),
|
58 |
('ent_coef', 'auto'),
|
59 |
('env_wrapper',
|
60 |
+
[{'gym.wrappers.time_limit.TimeLimit': {'max_episode_steps': 10000}},
|
61 |
+
'ae.wrapper.AutoencoderWrapper',
|
62 |
{'utils.wrappers.HistoryWrapper': {'horizon': 2}}]),
|
63 |
('gamma', 0.99),
|
64 |
('gradient_steps', 256),
|
|
|
92 |
'max_cte': 16,
|
93 |
'port': 9091,
|
94 |
'start_delay': 5.0},
|
95 |
+
'min_throttle': -0.2,
|
96 |
+
'steer': 0.3}
|
97 |
```
|
args.yml
CHANGED
@@ -11,6 +11,14 @@
|
|
11 |
- 120
|
12 |
- 160
|
13 |
- 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
frame_skip: 1
|
15 |
host: localhost
|
16 |
level: mountain_track
|
@@ -18,7 +26,8 @@
|
|
18 |
max_cte: 16
|
19 |
port: 9091
|
20 |
start_delay: 5.0
|
21 |
-
|
|
|
22 |
- - eval_episodes
|
23 |
- 5
|
24 |
- - eval_freq
|
@@ -26,11 +35,13 @@
|
|
26 |
- - gym_packages
|
27 |
- []
|
28 |
- - hyperparams
|
29 |
-
-
|
30 |
- - log_folder
|
31 |
- logs
|
32 |
- - log_interval
|
33 |
- -1
|
|
|
|
|
34 |
- - n_eval_envs
|
35 |
- 1
|
36 |
- - n_evaluations
|
@@ -47,16 +58,10 @@
|
|
47 |
- false
|
48 |
- - num_threads
|
49 |
- -1
|
50 |
-
- - offline_algo
|
51 |
-
- null
|
52 |
- - optimization_log_path
|
53 |
- null
|
54 |
- - optimize_hyperparameters
|
55 |
- false
|
56 |
-
- - pretrain_buffer
|
57 |
-
- null
|
58 |
-
- - pretrain_params
|
59 |
-
- null
|
60 |
- - pruner
|
61 |
- median
|
62 |
- - sampler
|
@@ -66,13 +71,13 @@
|
|
66 |
- - save_replay_buffer
|
67 |
- false
|
68 |
- - seed
|
69 |
-
-
|
70 |
- - storage
|
71 |
- null
|
72 |
- - study_name
|
73 |
- null
|
74 |
- - tensorboard_log
|
75 |
-
- runs/donkey-mountain-track-
|
76 |
- - track
|
77 |
- true
|
78 |
- - trained_agent
|
@@ -86,6 +91,6 @@
|
|
86 |
- - verbose
|
87 |
- 1
|
88 |
- - wandb_entity
|
89 |
-
-
|
90 |
- - wandb_project_name
|
91 |
- donkeycar
|
|
|
11 |
- 120
|
12 |
- 160
|
13 |
- 3
|
14 |
+
car_config:
|
15 |
+
body_rgb: !!python/tuple
|
16 |
+
- 226
|
17 |
+
- 112
|
18 |
+
- 18
|
19 |
+
body_style: donkey
|
20 |
+
car_name: Toni
|
21 |
+
font_size: 40
|
22 |
frame_skip: 1
|
23 |
host: localhost
|
24 |
level: mountain_track
|
|
|
26 |
max_cte: 16
|
27 |
port: 9091
|
28 |
start_delay: 5.0
|
29 |
+
min_throttle: -0.2
|
30 |
+
steer: 0.3
|
31 |
- - eval_episodes
|
32 |
- 5
|
33 |
- - eval_freq
|
|
|
35 |
- - gym_packages
|
36 |
- []
|
37 |
- - hyperparams
|
38 |
+
- null
|
39 |
- - log_folder
|
40 |
- logs
|
41 |
- - log_interval
|
42 |
- -1
|
43 |
+
- - max_total_trials
|
44 |
+
- null
|
45 |
- - n_eval_envs
|
46 |
- 1
|
47 |
- - n_evaluations
|
|
|
58 |
- false
|
59 |
- - num_threads
|
60 |
- -1
|
|
|
|
|
61 |
- - optimization_log_path
|
62 |
- null
|
63 |
- - optimize_hyperparameters
|
64 |
- false
|
|
|
|
|
|
|
|
|
65 |
- - pruner
|
66 |
- median
|
67 |
- - sampler
|
|
|
71 |
- - save_replay_buffer
|
72 |
- false
|
73 |
- - seed
|
74 |
+
- 1165537380
|
75 |
- - storage
|
76 |
- null
|
77 |
- - study_name
|
78 |
- null
|
79 |
- - tensorboard_log
|
80 |
+
- runs/donkey-mountain-track-v0__tqc__1165537380__1654422330
|
81 |
- - track
|
82 |
- true
|
83 |
- - trained_agent
|
|
|
91 |
- - verbose
|
92 |
- 1
|
93 |
- - wandb_entity
|
94 |
+
- sb3
|
95 |
- - wandb_project_name
|
96 |
- donkeycar
|
config.yml
CHANGED
@@ -10,7 +10,9 @@
|
|
10 |
- - ent_coef
|
11 |
- auto
|
12 |
- - env_wrapper
|
13 |
-
- -
|
|
|
|
|
14 |
- utils.wrappers.HistoryWrapper:
|
15 |
horizon: 2
|
16 |
- - gamma
|
|
|
10 |
- - ent_coef
|
11 |
- auto
|
12 |
- - env_wrapper
|
13 |
+
- - gym.wrappers.time_limit.TimeLimit:
|
14 |
+
max_episode_steps: 10000
|
15 |
+
- ae.wrapper.AutoencoderWrapper
|
16 |
- utils.wrappers.HistoryWrapper:
|
17 |
horizon: 2
|
18 |
- - gamma
|
env_kwargs.yml
CHANGED
@@ -18,4 +18,5 @@ conf:
|
|
18 |
max_cte: 16
|
19 |
port: 9091
|
20 |
start_delay: 5.0
|
21 |
-
|
|
|
|
18 |
max_cte: 16
|
19 |
port: 9091
|
20 |
start_delay: 5.0
|
21 |
+
min_throttle: -0.2
|
22 |
+
steer: 0.3
|
replay.mp4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08509c12d98dfd425ebb11fb4f4300e6e39370c9c233dad5cb13b63680ea1cf7
|
3 |
+
size 1499368
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 363.88236049999995, "std_reward": 0.9449308918473567, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-05T17:44:07.220665"}
|
tqc-donkey-mountain-track-v0.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3cd61e783173a83c2c39af9849940df04d7aa97d383f3a31c5ece07f4eb61bc
|
3 |
+
size 3969877
|
tqc-donkey-mountain-track-v0/actor.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32bd20c46c5e07ea560170aaafccad95ba5d30955469211b5f0037bebf5511d2
|
3 |
+
size 683835
|
tqc-donkey-mountain-track-v0/critic.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36d7bb586fe077766ba6747b5a6f4e2c07f7a4e7d95760743bffcbfd7e05e5ea
|
3 |
+
size 1460893
|
tqc-donkey-mountain-track-v0/data
CHANGED
@@ -4,17 +4,17 @@
|
|
4 |
":serialized:": "gASVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
|
5 |
"__module__": "sb3_contrib.tqc.policies",
|
6 |
"__doc__": "\n Policy class (with both actor and critic) for TQC.\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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 feature 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_quantiles: Number of quantiles for the critic.\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 ",
|
7 |
-
"__init__": "<function TQCPolicy.__init__ at
|
8 |
-
"_build": "<function TQCPolicy._build at
|
9 |
-
"_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at
|
10 |
-
"reset_noise": "<function TQCPolicy.reset_noise at
|
11 |
-
"make_actor": "<function TQCPolicy.make_actor at
|
12 |
-
"make_critic": "<function TQCPolicy.make_critic at
|
13 |
-
"forward": "<function TQCPolicy.forward at
|
14 |
-
"_predict": "<function TQCPolicy._predict at
|
15 |
-
"set_training_mode": "<function TQCPolicy.set_training_mode at
|
16 |
"__abstractmethods__": "frozenset()",
|
17 |
-
"_abc_impl": "<_abc_data object at
|
18 |
},
|
19 |
"verbose": 1,
|
20 |
"policy_kwargs": {
|
@@ -29,26 +29,26 @@
|
|
29 |
},
|
30 |
"observation_space": {
|
31 |
":type:": "<class 'gym.spaces.box.Box'>",
|
32 |
-
":serialized:": "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
|
33 |
"dtype": "float32",
|
34 |
"_shape": [
|
35 |
70
|
36 |
],
|
37 |
-
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -0.
|
38 |
-
"high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf 0.
|
39 |
"bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False True True True True]",
|
40 |
"bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False True True True True]",
|
41 |
"_np_random": null
|
42 |
},
|
43 |
"action_space": {
|
44 |
":type:": "<class 'gym.spaces.box.Box'>",
|
45 |
-
":serialized:": "gASVFwwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////
|
46 |
"dtype": "float32",
|
47 |
"_shape": [
|
48 |
2
|
49 |
],
|
50 |
-
"low": "[-0.
|
51 |
-
"high": "[0.
|
52 |
"bounded_below": "[ True True]",
|
53 |
"bounded_above": "[ True True]",
|
54 |
"_np_random": "RandomState(MT19937)"
|
@@ -59,12 +59,12 @@
|
|
59 |
"_num_timesteps_at_start": 0,
|
60 |
"seed": 0,
|
61 |
"action_noise": null,
|
62 |
-
"start_time":
|
63 |
"learning_rate": {
|
64 |
":type:": "<class 'function'>",
|
65 |
":serialized:": "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"
|
66 |
},
|
67 |
-
"tensorboard_log": "runs/donkey-mountain-track-
|
68 |
"lr_schedule": {
|
69 |
":type:": "<class 'function'>",
|
70 |
":serialized:": "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"
|
@@ -76,7 +76,7 @@
|
|
76 |
},
|
77 |
"_last_original_obs": {
|
78 |
":type:": "<class 'numpy.ndarray'>",
|
79 |
-
":serialized:": "gASVpQEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLRoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////
|
80 |
},
|
81 |
"_episode_num": 0,
|
82 |
"use_sde": true,
|
@@ -90,7 +90,7 @@
|
|
90 |
":type:": "<class 'collections.deque'>",
|
91 |
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
92 |
},
|
93 |
-
"_n_updates":
|
94 |
"buffer_size": 1,
|
95 |
"batch_size": 256,
|
96 |
"learning_starts": 500,
|
@@ -103,12 +103,12 @@
|
|
103 |
":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
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:\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 :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
|
107 |
-
"add": "<function ReplayBuffer.add at
|
108 |
-
"sample": "<function ReplayBuffer.sample at
|
109 |
-
"_get_samples": "<function ReplayBuffer._get_samples at
|
110 |
"__abstractmethods__": "frozenset()",
|
111 |
-
"_abc_impl": "<_abc_data object at
|
112 |
},
|
113 |
"replay_buffer_kwargs": {},
|
114 |
"train_freq": {
|
|
|
4 |
":serialized:": "gASVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
|
5 |
"__module__": "sb3_contrib.tqc.policies",
|
6 |
"__doc__": "\n Policy class (with both actor and critic) for TQC.\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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 feature 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_quantiles: Number of quantiles for the critic.\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 ",
|
7 |
+
"__init__": "<function TQCPolicy.__init__ at 0x7f4d85780560>",
|
8 |
+
"_build": "<function TQCPolicy._build at 0x7f4d857805f0>",
|
9 |
+
"_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f4d85780680>",
|
10 |
+
"reset_noise": "<function TQCPolicy.reset_noise at 0x7f4d85780710>",
|
11 |
+
"make_actor": "<function TQCPolicy.make_actor at 0x7f4d857807a0>",
|
12 |
+
"make_critic": "<function TQCPolicy.make_critic at 0x7f4d85780830>",
|
13 |
+
"forward": "<function TQCPolicy.forward at 0x7f4d857808c0>",
|
14 |
+
"_predict": "<function TQCPolicy._predict at 0x7f4d85780950>",
|
15 |
+
"set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f4d857809e0>",
|
16 |
"__abstractmethods__": "frozenset()",
|
17 |
+
"_abc_impl": "<_abc_data object at 0x7f4d8577d1e0>"
|
18 |
},
|
19 |
"verbose": 1,
|
20 |
"policy_kwargs": {
|
|
|
29 |
},
|
30 |
"observation_space": {
|
31 |
":type:": "<class 'gym.spaces.box.Box'>",
|
32 |
+
":serialized:": "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",
|
33 |
"dtype": "float32",
|
34 |
"_shape": [
|
35 |
70
|
36 |
],
|
37 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -0.3 -0.3 -0.2 -0.2]",
|
38 |
+
"high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf 0.3 0.3 1. 1. ]",
|
39 |
"bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False True True True True]",
|
40 |
"bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False True True True True]",
|
41 |
"_np_random": null
|
42 |
},
|
43 |
"action_space": {
|
44 |
":type:": "<class 'gym.spaces.box.Box'>",
|
45 |
+
":serialized:": "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",
|
46 |
"dtype": "float32",
|
47 |
"_shape": [
|
48 |
2
|
49 |
],
|
50 |
+
"low": "[-0.3 -0.2]",
|
51 |
+
"high": "[0.3 1. ]",
|
52 |
"bounded_below": "[ True True]",
|
53 |
"bounded_above": "[ True True]",
|
54 |
"_np_random": "RandomState(MT19937)"
|
|
|
59 |
"_num_timesteps_at_start": 0,
|
60 |
"seed": 0,
|
61 |
"action_noise": null,
|
62 |
+
"start_time": 1654422341.1686037,
|
63 |
"learning_rate": {
|
64 |
":type:": "<class 'function'>",
|
65 |
":serialized:": "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"
|
66 |
},
|
67 |
+
"tensorboard_log": "runs/donkey-mountain-track-v0__tqc__1165537380__1654422330/donkey-mountain-track-v0",
|
68 |
"lr_schedule": {
|
69 |
":type:": "<class 'function'>",
|
70 |
":serialized:": "gASVywIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxOL2hvbWUvYW50b25pbi9Eb2N1bWVudHMvcmwvc3RhYmxlLWJhc2VsaW5lczMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxOL2hvbWUvYW50b25pbi9Eb2N1bWVudHMvcmwvc3RhYmxlLWJhc2VsaW5lczMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9H668QI2OyhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
|
|
76 |
},
|
77 |
"_last_original_obs": {
|
78 |
":type:": "<class 'numpy.ndarray'>",
|
79 |
+
":serialized:": "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"
|
80 |
},
|
81 |
"_episode_num": 0,
|
82 |
"use_sde": true,
|
|
|
90 |
":type:": "<class 'collections.deque'>",
|
91 |
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
92 |
},
|
93 |
+
"_n_updates": 1622600,
|
94 |
"buffer_size": 1,
|
95 |
"batch_size": 256,
|
96 |
"learning_starts": 500,
|
|
|
103 |
":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
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:\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 :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 0x7f4d86024170>",
|
107 |
+
"add": "<function ReplayBuffer.add at 0x7f4d86024200>",
|
108 |
+
"sample": "<function ReplayBuffer.sample at 0x7f4d85b89d40>",
|
109 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7f4d85b89dd0>",
|
110 |
"__abstractmethods__": "frozenset()",
|
111 |
+
"_abc_impl": "<_abc_data object at 0x7f4d8606b690>"
|
112 |
},
|
113 |
"replay_buffer_kwargs": {},
|
114 |
"train_freq": {
|
tqc-donkey-mountain-track-v0/ent_coef_optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b330e96042fbbc7c63ebb98de98cf5ccf10555e12ed6f49e3ad3651724c04589
|
3 |
+
size 1255
|
tqc-donkey-mountain-track-v0/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe37d0e0e10b1b5ec80be27d722164764f0c5dea58044d9ffbd4fe3806222794
|
3 |
+
size 1804936
|
tqc-donkey-mountain-track-v0/pytorch_variables.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 747
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d00ff1a7756f6ad9e3006a2cbc2d14dddfc3656a5693f57fe614814f9b538f25
|
3 |
size 747
|
tqc-donkey-mountain-track-v0/system_info.txt
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
OS: Linux-5.
|
2 |
-
Python: 3.7.
|
3 |
Stable-Baselines3: 1.5.1a8
|
4 |
-
PyTorch: 1.11.0
|
5 |
-
GPU Enabled:
|
6 |
-
Numpy: 1.21.
|
7 |
Gym: 0.21.0
|
|
|
1 |
+
OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
|
2 |
+
Python: 3.7.10
|
3 |
Stable-Baselines3: 1.5.1a8
|
4 |
+
PyTorch: 1.11.0
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.2
|
7 |
Gym: 0.21.0
|
train_eval_metrics.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fcbecf4511c020477a37bf9b486a555e51319c4bdf4eb65d95c842d5515dac4
|
3 |
+
size 26826
|
vec_normalize.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6373
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:626022b029b0e22cd45d435ebdee2fe3ba1a48bc1a1cf839f6c3bdedda17df14
|
3 |
size 6373
|