araffin commited on
Commit
2581dd3
1 Parent(s): ee2bb8b

Initial commit

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - HalfCheetahBulletEnv-v0
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: TQC
10
+ results:
11
+ - metrics:
12
+ - type: mean_reward
13
+ value: 3665.83 +/- 28.42
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: HalfCheetahBulletEnv-v0
20
+ type: HalfCheetahBulletEnv-v0
21
+ ---
22
+
23
+ # **TQC** Agent playing **HalfCheetahBulletEnv-v0**
24
+ This is a trained model of a **TQC** agent playing **HalfCheetahBulletEnv-v0**
25
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
26
+ and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
27
+
28
+ The RL Zoo is a training framework for Stable Baselines3
29
+ reinforcement learning agents,
30
+ with hyperparameter optimization and pre-trained agents included.
31
+
32
+ ## Usage (with SB3 RL Zoo)
33
+
34
+ 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
+ ```
39
+ # Download model and save it into the logs/ folder
40
+ python -m utils.load_from_hub --algo tqc --env HalfCheetahBulletEnv-v0 -orga sb3 -f logs/
41
+ python enjoy.py --algo tqc --env HalfCheetahBulletEnv-v0 -f logs/
42
+ ```
43
+
44
+ ## Training (with the RL Zoo)
45
+ ```
46
+ python train.py --algo tqc --env HalfCheetahBulletEnv-v0 -f logs/
47
+ # Upload the model and generate video (when possible)
48
+ python -m utils.push_to_hub --algo tqc --env HalfCheetahBulletEnv-v0 -f logs/ -orga sb3
49
+ ```
50
+
51
+ ## Hyperparameters
52
+ ```python
53
+ OrderedDict([('batch_size', 256),
54
+ ('buffer_size', 300000),
55
+ ('ent_coef', 'auto'),
56
+ ('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
57
+ ('gamma', 0.98),
58
+ ('gradient_steps', 64),
59
+ ('learning_rate', 0.00073),
60
+ ('learning_starts', 10000),
61
+ ('n_timesteps', 1000000.0),
62
+ ('policy', 'MlpPolicy'),
63
+ ('policy_kwargs', 'dict(log_std_init=-3, net_arch=[400, 300])'),
64
+ ('tau', 0.02),
65
+ ('train_freq', 64),
66
+ ('use_sde', True),
67
+ ('normalize', False)])
68
+ ```
args.yml ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - tqc
4
+ - - env
5
+ - HalfCheetahBulletEnv-v0
6
+ - - env_kwargs
7
+ - null
8
+ - - eval_episodes
9
+ - 10
10
+ - - eval_freq
11
+ - 10000
12
+ - - gym_packages
13
+ - []
14
+ - - hyperparams
15
+ - null
16
+ - - log_folder
17
+ - rl-trained-agents/
18
+ - - log_interval
19
+ - -1
20
+ - - n_evaluations
21
+ - 20
22
+ - - n_jobs
23
+ - 1
24
+ - - n_startup_trials
25
+ - 10
26
+ - - n_timesteps
27
+ - -1
28
+ - - n_trials
29
+ - 10
30
+ - - num_threads
31
+ - -1
32
+ - - optimize_hyperparameters
33
+ - false
34
+ - - pruner
35
+ - median
36
+ - - sampler
37
+ - tpe
38
+ - - save_freq
39
+ - -1
40
+ - - save_replay_buffer
41
+ - false
42
+ - - seed
43
+ - 1414476981
44
+ - - storage
45
+ - null
46
+ - - study_name
47
+ - null
48
+ - - tensorboard_log
49
+ - ''
50
+ - - trained_agent
51
+ - ''
52
+ - - truncate_last_trajectory
53
+ - true
54
+ - - uuid
55
+ - true
56
+ - - vec_env
57
+ - dummy
58
+ - - verbose
59
+ - 1
config.yml ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 256
4
+ - - buffer_size
5
+ - 300000
6
+ - - ent_coef
7
+ - auto
8
+ - - env_wrapper
9
+ - sb3_contrib.common.wrappers.TimeFeatureWrapper
10
+ - - gamma
11
+ - 0.98
12
+ - - gradient_steps
13
+ - 64
14
+ - - learning_rate
15
+ - 0.00073
16
+ - - learning_starts
17
+ - 10000
18
+ - - n_timesteps
19
+ - 1000000.0
20
+ - - policy
21
+ - MlpPolicy
22
+ - - policy_kwargs
23
+ - dict(log_std_init=-3, net_arch=[400, 300])
24
+ - - tau
25
+ - 0.02
26
+ - - train_freq
27
+ - 64
28
+ - - use_sde
29
+ - true
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1b8339f372c264a26d3898d1109b903d234db66b17d81668afd47cb59b2c67b
3
+ size 1256093
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 3665.8284263, "std_reward": 28.4187642297266, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T20:58:32.653379"}
tqc-HalfCheetahBulletEnv-v0.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eaf7a7bf240c27841d97e3f1a490d1d514d82ea81282be0be7eb658a07b18da
3
+ size 6189884
tqc-HalfCheetahBulletEnv-v0/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.5.1a8
tqc-HalfCheetahBulletEnv-v0/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10489b6ac7d517ae3f28df1d4b91e9e1d5e4d33db03ce9fa7bf971890a98a5c4
3
+ size 1084603
tqc-HalfCheetahBulletEnv-v0/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23db51ee00f86321ec31a3a7edb37471f103c8c9da61cdafd736e2c3d4cf9fa5
3
+ size 2269085
tqc-HalfCheetahBulletEnv-v0/data ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
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 0x7fdf03647710>",
8
+ "_build": "<function TQCPolicy._build at 0x7fdf036477a0>",
9
+ "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7fdf03647830>",
10
+ "reset_noise": "<function TQCPolicy.reset_noise at 0x7fdf036478c0>",
11
+ "make_actor": "<function TQCPolicy.make_actor at 0x7fdf03647950>",
12
+ "make_critic": "<function TQCPolicy.make_critic at 0x7fdf036479e0>",
13
+ "forward": "<function TQCPolicy.forward at 0x7fdf03647a70>",
14
+ "_predict": "<function TQCPolicy._predict at 0x7fdf03647b00>",
15
+ "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7fdf03647b90>",
16
+ "__abstractmethods__": "frozenset()",
17
+ "_abc_impl": "<_abc_data object at 0x7fdf036a7690>"
18
+ },
19
+ "verbose": 1,
20
+ "policy_kwargs": {
21
+ "log_std_init": -3,
22
+ "net_arch": [
23
+ 400,
24
+ 300
25
+ ],
26
+ "use_sde": true
27
+ },
28
+ "observation_space": {
29
+ ":type:": "<class 'gym.spaces.box.Box'>",
30
+ ":serialized:": "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",
31
+ "dtype": "float32",
32
+ "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 0.]",
33
+ "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 1.]",
34
+ "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 True]",
35
+ "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 True]",
36
+ "_np_random": null,
37
+ "_shape": [
38
+ 27
39
+ ]
40
+ },
41
+ "action_space": {
42
+ ":type:": "<class 'gym.spaces.box.Box'>",
43
+ ":serialized:": "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",
44
+ "dtype": "float32",
45
+ "low": "[-1. -1. -1. -1. -1. -1.]",
46
+ "high": "[1. 1. 1. 1. 1. 1.]",
47
+ "bounded_below": "[ True True True True True True]",
48
+ "bounded_above": "[ True True True True True True]",
49
+ "_np_random": "RandomState(MT19937)",
50
+ "_shape": [
51
+ 6
52
+ ]
53
+ },
54
+ "n_envs": 1,
55
+ "num_timesteps": 1000000,
56
+ "_total_timesteps": 1000000,
57
+ "_num_timesteps_at_start": 0,
58
+ "seed": 0,
59
+ "action_noise": null,
60
+ "start_time": 1614621389.675964,
61
+ "learning_rate": {
62
+ ":type:": "<class 'function'>",
63
+ ":serialized:": "gASV2QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxVL3ZvbHVtZS9VU0VSU1RPUkUvcmFmZl9hbi9wcm9qZWN0cy90b3JjaHktYmFzZWxpbmVzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS3xDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVS92b2x1bWUvVVNFUlNUT1JFL3JhZmZfYW4vcHJvamVjdHMvdG9yY2h5LWJhc2VsaW5lcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIH2UfZQoaBdoDowMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP0frrxAjY7KFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
64
+ },
65
+ "tensorboard_log": null,
66
+ "lr_schedule": {
67
+ ":type:": "<class 'function'>",
68
+ ":serialized:": "gASV2QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxVL3ZvbHVtZS9VU0VSU1RPUkUvcmFmZl9hbi9wcm9qZWN0cy90b3JjaHktYmFzZWxpbmVzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS3xDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVS92b2x1bWUvVVNFUlNUT1JFL3JhZmZfYW4vcHJvamVjdHMvdG9yY2h5LWJhc2VsaW5lcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIH2UfZQoaBdoDowMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP0frrxAjY7KFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
69
+ },
70
+ "_last_obs": null,
71
+ "_last_episode_starts": null,
72
+ "_last_original_obs": {
73
+ ":type:": "<class 'numpy.ndarray'>",
74
+ ":serialized:": "gASV9gAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLG4aUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUNsBJUXvgAAAAAAAIA/LGzQPwAAAACWS3S9AAAAACAUDr5SB1U/zIGQP1jnjL6PM++/WqBEvslojj9HYlo/EiR4PoKwpD5hixC+54gUP9niDL4AAAAAAAAAAAAAAAAAAIA/AAAAAAAAAABvEoM6lHSUYi4="
75
+ },
76
+ "_episode_num": 1000,
77
+ "use_sde": true,
78
+ "sde_sample_freq": -1,
79
+ "_current_progress_remaining": 0.0,
80
+ "ep_info_buffer": {
81
+ ":type:": "<class 'collections.deque'>",
82
+ ":serialized:": "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"
83
+ },
84
+ "ep_success_buffer": {
85
+ ":type:": "<class 'collections.deque'>",
86
+ ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
87
+ },
88
+ "_n_updates": 990016,
89
+ "buffer_size": 1,
90
+ "batch_size": 256,
91
+ "learning_starts": 10000,
92
+ "tau": 0.02,
93
+ "gamma": 0.98,
94
+ "gradient_steps": 64,
95
+ "optimize_memory_usage": false,
96
+ "replay_buffer_class": {
97
+ ":type:": "<class 'abc.ABCMeta'>",
98
+ ":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
99
+ "__module__": "stable_baselines3.common.buffers",
100
+ "__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 ",
101
+ "__init__": "<function ReplayBuffer.__init__ at 0x7fdf03e21b90>",
102
+ "add": "<function ReplayBuffer.add at 0x7fdf03e21c20>",
103
+ "sample": "<function ReplayBuffer.sample at 0x7fdf039877a0>",
104
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x7fdf03987830>",
105
+ "__abstractmethods__": "frozenset()",
106
+ "_abc_impl": "<_abc_data object at 0x7fdf03e795d0>"
107
+ },
108
+ "replay_buffer_kwargs": {},
109
+ "train_freq": {
110
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
111
+ ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
112
+ },
113
+ "use_sde_at_warmup": false,
114
+ "target_entropy": -6.0,
115
+ "ent_coef": "auto",
116
+ "target_update_interval": 1,
117
+ "top_quantiles_to_drop_per_net": 2,
118
+ "_last_dones": {
119
+ ":type:": "<class 'numpy.ndarray'>",
120
+ ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
121
+ },
122
+ "remove_time_limit_termination": false
123
+ }
tqc-HalfCheetahBulletEnv-v0/ent_coef_optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e053fe3ecd4af75662589a89e94b04d643fb0a4e46deb498e13776ff167fd308
3
+ size 1255
tqc-HalfCheetahBulletEnv-v0/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff62ff0ee624e8d3d4cfd19802b463f52fdfc0cd9baf9a86fd10031c389a04ac
3
+ size 2813448
tqc-HalfCheetahBulletEnv-v0/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c2732bf889673392a2df783ba7c672424e9c533cdc8e6b122a6835b6e0211c
3
+ size 747
tqc-HalfCheetahBulletEnv-v0/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3ee36ff4a9504eed6a57e44f682954b97104094d97e81ee3a788279defc209
3
+ size 48044