araffin commited on
Commit
79e5c71
1 Parent(s): 2782562

Initial commit

Browse files
.gitattributes CHANGED
@@ -25,3 +25,5 @@ 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
29
+ vec_normalize.pkl filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - donkey-warren-track-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: 175.85 +/- 2.78
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: donkey-warren-track-v0
20
+ type: donkey-warren-track-v0
21
+ ---
22
+
23
+ # **TQC** Agent playing **donkey-warren-track-v0**
24
+ This is a trained model of a **TQC** agent playing **donkey-warren-track-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 donkey-warren-track-v0 -orga araffin -f logs/
41
+ python enjoy.py --algo tqc --env donkey-warren-track-v0 -f logs/
42
+ ```
43
+
44
+ ## Training (with the RL Zoo)
45
+ ```
46
+ python train.py --algo tqc --env donkey-warren-track-v0 -f logs/
47
+ # Upload the model and generate video (when possible)
48
+ python -m utils.push_to_hub --algo tqc --env donkey-warren-track-v0 -f logs/ -orga araffin
49
+ ```
50
+
51
+ ## Hyperparameters
52
+ ```python
53
+ OrderedDict([('batch_size', 256),
54
+ ('buffer_size', 200000),
55
+ ('callback',
56
+ [{'utils.callbacks.ParallelTrainCallback': {'gradient_steps': 200}},
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),
65
+ ('learning_rate', 0.00073),
66
+ ('learning_starts', 500),
67
+ ('n_timesteps', 2000000.0),
68
+ ('normalize', "{'norm_obs': True, 'norm_reward': False}"),
69
+ ('policy', 'MlpPolicy'),
70
+ ('policy_kwargs',
71
+ 'dict(log_std_init=-3, net_arch=[256, 256], n_critics=2, '
72
+ 'use_expln=True)'),
73
+ ('sde_sample_freq', 16),
74
+ ('tau', 0.02),
75
+ ('train_freq', 200),
76
+ ('use_sde', True),
77
+ ('use_sde_at_warmup', True),
78
+ ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
79
+ ```
80
+
81
+ # Environment Arguments
82
+ ```python
83
+ {'conf': {'cam_resolution': (120, 160, 3),
84
+ 'car_config': {'body_rgb': (226, 112, 18),
85
+ 'body_style': 'donkey',
86
+ 'car_name': 'Toni',
87
+ 'font_size': 40},
88
+ 'frame_skip': 1,
89
+ 'host': 'localhost',
90
+ 'level': 'warren',
91
+ 'log_level': 20,
92
+ 'max_cte': 8,
93
+ 'port': 9091,
94
+ 'start_delay': 5.0},
95
+ 'min_throttle': -0.2,
96
+ 'steer': 0.8}
97
+ ```
args.yml ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - tqc
4
+ - - device
5
+ - auto
6
+ - - env
7
+ - donkey-warren-track-v0
8
+ - - env_kwargs
9
+ - conf:
10
+ cam_resolution: !!python/tuple
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: warren
25
+ log_level: 20
26
+ max_cte: 8
27
+ port: 9091
28
+ start_delay: 5.0
29
+ min_throttle: -0.2
30
+ steer: 0.8
31
+ - - eval_episodes
32
+ - 5
33
+ - - eval_freq
34
+ - -1
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
48
+ - null
49
+ - - n_jobs
50
+ - 1
51
+ - - n_startup_trials
52
+ - 10
53
+ - - n_timesteps
54
+ - -1
55
+ - - n_trials
56
+ - 500
57
+ - - no_optim_plots
58
+ - false
59
+ - - num_threads
60
+ - -1
61
+ - - optimization_log_path
62
+ - null
63
+ - - optimize_hyperparameters
64
+ - false
65
+ - - pruner
66
+ - median
67
+ - - sampler
68
+ - tpe
69
+ - - save_freq
70
+ - 25000
71
+ - - save_replay_buffer
72
+ - false
73
+ - - seed
74
+ - 2529849244
75
+ - - storage
76
+ - null
77
+ - - study_name
78
+ - null
79
+ - - tensorboard_log
80
+ - runs/donkey-warren-track-v0__tqc__2529849244__1655634920
81
+ - - track
82
+ - true
83
+ - - trained_agent
84
+ - logs/tqc/donkey-minimonaco-track-v0_12/donkey-minimonaco-track-v0.zip
85
+ - - truncate_last_trajectory
86
+ - true
87
+ - - uuid
88
+ - false
89
+ - - vec_env
90
+ - dummy
91
+ - - verbose
92
+ - 1
93
+ - - wandb_entity
94
+ - sb3
95
+ - - wandb_project_name
96
+ - donkeycar
config.yml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 256
4
+ - - buffer_size
5
+ - 200000
6
+ - - callback
7
+ - - utils.callbacks.ParallelTrainCallback:
8
+ gradient_steps: 200
9
+ - utils.callbacks.LapTimeCallback
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
19
+ - 0.99
20
+ - - gradient_steps
21
+ - 256
22
+ - - learning_rate
23
+ - 0.00073
24
+ - - learning_starts
25
+ - 500
26
+ - - n_timesteps
27
+ - 2000000.0
28
+ - - normalize
29
+ - '{''norm_obs'': True, ''norm_reward'': False}'
30
+ - - policy
31
+ - MlpPolicy
32
+ - - policy_kwargs
33
+ - dict(log_std_init=-3, net_arch=[256, 256], n_critics=2, use_expln=True)
34
+ - - sde_sample_freq
35
+ - 16
36
+ - - tau
37
+ - 0.02
38
+ - - train_freq
39
+ - 200
40
+ - - use_sde
41
+ - true
42
+ - - use_sde_at_warmup
43
+ - true
env_kwargs.yml ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ conf:
2
+ cam_resolution: !!python/tuple
3
+ - 120
4
+ - 160
5
+ - 3
6
+ car_config:
7
+ body_rgb: !!python/tuple
8
+ - 226
9
+ - 112
10
+ - 18
11
+ body_style: donkey
12
+ car_name: Toni
13
+ font_size: 40
14
+ frame_skip: 1
15
+ host: localhost
16
+ level: warren
17
+ log_level: 20
18
+ max_cte: 8
19
+ port: 9091
20
+ start_delay: 5.0
21
+ min_throttle: -0.2
22
+ steer: 0.8
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43f12c2c1901e328536da7fc76512b2bd7b9f500896bd95858b7ddb678db3b51
3
+ size 1608142
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 175.85419530000001, "std_reward": 2.7763180707583968, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-19T13:43:19.584155"}
tqc-donkey-warren-track-v0.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e36954bfb2b6893b312338644ebaec4c26aea064cb21699a2d574608a13186a5
3
+ size 3969872
tqc-donkey-warren-track-v0/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.5.1a9
tqc-donkey-warren-track-v0/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b2baad7fb4100f9f6c9e8acd9ecb6c170ade45b2001ab80464244463f242f36
3
+ size 683835
tqc-donkey-warren-track-v0/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb2a8c7d6b20a53263d46301f3e429ea68284ee46ba79a3c3e02b0cb4066d42
3
+ size 1460893
tqc-donkey-warren-track-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 0x7fa38ae877a0>",
8
+ "_build": "<function TQCPolicy._build at 0x7fa38ae87830>",
9
+ "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7fa38ae878c0>",
10
+ "reset_noise": "<function TQCPolicy.reset_noise at 0x7fa38ae87950>",
11
+ "make_actor": "<function TQCPolicy.make_actor at 0x7fa38ae879e0>",
12
+ "make_critic": "<function TQCPolicy.make_critic at 0x7fa38ae87a70>",
13
+ "forward": "<function TQCPolicy.forward at 0x7fa38ae87b00>",
14
+ "_predict": "<function TQCPolicy._predict at 0x7fa38ae87b90>",
15
+ "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7fa38ae87c20>",
16
+ "__abstractmethods__": "frozenset()",
17
+ "_abc_impl": "<_abc_data object at 0x7fa38ae85270>"
18
+ },
19
+ "verbose": 1,
20
+ "policy_kwargs": {
21
+ "log_std_init": -3,
22
+ "net_arch": [
23
+ 256,
24
+ 256
25
+ ],
26
+ "n_critics": 2,
27
+ "use_expln": true,
28
+ "use_sde": true
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 -0.8 -0.8 -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 0.8 0.8 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": "[-0.8 -0.2]",
51
+ "high": "[0.8 1. ]",
52
+ "bounded_below": "[ True True]",
53
+ "bounded_above": "[ True True]",
54
+ "_np_random": "RandomState(MT19937)"
55
+ },
56
+ "n_envs": 1,
57
+ "num_timesteps": 0,
58
+ "_total_timesteps": 2000000,
59
+ "_num_timesteps_at_start": 0,
60
+ "seed": 0,
61
+ "action_noise": null,
62
+ "start_time": 1655634929.8535643,
63
+ "learning_rate": {
64
+ ":type:": "<class 'function'>",
65
+ ":serialized:": "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"
66
+ },
67
+ "tensorboard_log": "runs/donkey-warren-track-v0__tqc__2529849244__1655634920/donkey-warren-track-v0",
68
+ "lr_schedule": {
69
+ ":type:": "<class 'function'>",
70
+ ":serialized:": "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"
71
+ },
72
+ "_last_obs": null,
73
+ "_last_episode_starts": {
74
+ ":type:": "<class 'numpy.ndarray'>",
75
+ ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
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,
83
+ "sde_sample_freq": 16,
84
+ "_current_progress_remaining": 1,
85
+ "ep_info_buffer": {
86
+ ":type:": "<class 'collections.deque'>",
87
+ ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
88
+ },
89
+ "ep_success_buffer": {
90
+ ":type:": "<class 'collections.deque'>",
91
+ ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
92
+ },
93
+ "_n_updates": 703200,
94
+ "buffer_size": 1,
95
+ "batch_size": 256,
96
+ "learning_starts": 500,
97
+ "tau": 0.02,
98
+ "gamma": 0.99,
99
+ "gradient_steps": 256,
100
+ "optimize_memory_usage": false,
101
+ "replay_buffer_class": {
102
+ ":type:": "<class 'abc.ABCMeta'>",
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 0x7fa38b72e3b0>",
107
+ "add": "<function ReplayBuffer.add at 0x7fa38b72e440>",
108
+ "sample": "<function ReplayBuffer.sample at 0x7fa38b292f80>",
109
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x7fa38b294050>",
110
+ "__abstractmethods__": "frozenset()",
111
+ "_abc_impl": "<_abc_data object at 0x7fa38b775720>"
112
+ },
113
+ "replay_buffer_kwargs": {},
114
+ "train_freq": {
115
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
116
+ ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLyGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
117
+ },
118
+ "use_sde_at_warmup": true,
119
+ "target_entropy": -2.0,
120
+ "ent_coef": "auto",
121
+ "target_update_interval": 1,
122
+ "top_quantiles_to_drop_per_net": 2
123
+ }
tqc-donkey-warren-track-v0/ent_coef_optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18bfe45d469a1d901b9d8f5ca9368adee41939e258775353abf59a5456e1cb19
3
+ size 1255
tqc-donkey-warren-track-v0/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05de3ae09c6a3c36b7db1a9fa1e2fd360a5481a250deffaf1709efc4355c7551
3
+ size 1804936
tqc-donkey-warren-track-v0/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d60a6993dd9d590e543b4132d313887fd4be4168fbc0be11799e21aa6a27a2d
3
+ size 747
tqc-donkey-warren-track-v0/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ OS: Linux-5.13.0-51-generic-x86_64-with-debian-bullseye-sid #58~20.04.1-Ubuntu SMP Tue Jun 14 11:29:12 UTC 2022
2
+ Python: 3.7.10
3
+ Stable-Baselines3: 1.5.1a9
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:dab44c0b9543709885847a6b5bc07382317a5dcd382645a1e81c9f12ec1a6740
3
+ size 2862
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d563ca272807a56c0f4a3e43c9a5f6408985f4f075e0d4d752751777ca898a
3
+ size 6373