Quentin Gallouédec commited on
Commit
2c48868
1 Parent(s): 6e73fff

Initial commit

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - Hopper-v3
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: TQC
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: Hopper-v3
16
+ type: Hopper-v3
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 3726.60 +/- 10.89
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **TQC** Agent playing **Hopper-v3**
25
+ This is a trained model of a **TQC** agent playing **Hopper-v3**
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 tqc --env Hopper-v3 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo tqc --env Hopper-v3 -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 tqc --env Hopper-v3 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo tqc --env Hopper-v3 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo tqc --env Hopper-v3 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo tqc --env Hopper-v3 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('learning_starts', 10000),
66
+ ('n_timesteps', 1000000.0),
67
+ ('policy', 'MlpPolicy'),
68
+ ('top_quantiles_to_drop_per_net', 5),
69
+ ('normalize', False)])
70
+ ```
args.yml ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - tqc
4
+ - - conf_file
5
+ - null
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - Hopper-v3
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 20
14
+ - - eval_freq
15
+ - 25000
16
+ - - gym_packages
17
+ - []
18
+ - - hyperparams
19
+ - null
20
+ - - log_folder
21
+ - logs
22
+ - - log_interval
23
+ - -1
24
+ - - max_total_trials
25
+ - null
26
+ - - n_eval_envs
27
+ - 5
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
+ - -1
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
+ - 1346000078
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - runs/Hopper-v3__tqc__1346000078__1675976919
64
+ - - track
65
+ - true
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
+ - openrlbenchmark
78
+ - - wandb_project_name
79
+ - sb3
80
+ - - wandb_tags
81
+ - []
82
+ - - yaml_file
83
+ - null
config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - learning_starts
3
+ - 10000
4
+ - - n_timesteps
5
+ - 1000000.0
6
+ - - policy
7
+ - MlpPolicy
8
+ - - top_quantiles_to_drop_per_net
9
+ - 5
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:ce717ec9cafd59279c298e516cce0da14c0ee6fcea852c46eed67e492b95b555
3
+ size 1446033
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 3726.6049652999995, "std_reward": 10.894630518656424, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T16:09:42.400846"}
tqc-Hopper-v3.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91558b9ae580108e2b4428aac86a36905e9d7e6891fd7f01953a044c4a348146
3
+ size 3328135
tqc-Hopper-v3/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
tqc-Hopper-v3/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3564afde38339c2421b4fce1bd2a565caa81e50c5b047f59bc0195611bc28c71
3
+ size 569757
tqc-Hopper-v3/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015cd6851ff4014d374a5f69c6648061ae401a7ac0dac327c610d6091cb328d8
3
+ size 1226489
tqc-Hopper-v3/data ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gAWVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
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 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 0x7fe705eea670>",
8
+ "_build": "<function TQCPolicy._build at 0x7fe705eea700>",
9
+ "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7fe705eea790>",
10
+ "reset_noise": "<function TQCPolicy.reset_noise at 0x7fe705eea820>",
11
+ "make_actor": "<function TQCPolicy.make_actor at 0x7fe705eea8b0>",
12
+ "make_critic": "<function TQCPolicy.make_critic at 0x7fe705eea940>",
13
+ "forward": "<function TQCPolicy.forward at 0x7fe705eea9d0>",
14
+ "_predict": "<function TQCPolicy._predict at 0x7fe705eeaa60>",
15
+ "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7fe705eeaaf0>",
16
+ "__abstractmethods__": "frozenset()",
17
+ "_abc_impl": "<_abc._abc_data object at 0x7fe705ee8d40>"
18
+ },
19
+ "verbose": 1,
20
+ "policy_kwargs": {
21
+ "use_sde": false
22
+ },
23
+ "observation_space": {
24
+ ":type:": "<class 'gym.spaces.box.Box'>",
25
+ ":serialized:": "gAWVFQIAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLC4WUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWWAAAAAAAAAAAAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/lGgKSwuFlIwBQ5R0lFKUjARoaWdolGgSKJZYAAAAAAAAAAAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H+UaApLC4WUaBV0lFKUjA1ib3VuZGVkX2JlbG93lGgSKJYLAAAAAAAAAAAAAAAAAAAAAAAAlGgHjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwuFlGgVdJRSlIwNYm91bmRlZF9hYm92ZZRoEiiWCwAAAAAAAAAAAAAAAAAAAAAAAJRoIUsLhZRoFXSUUpSMCl9ucF9yYW5kb22UTnViLg==",
26
+ "dtype": "float64",
27
+ "_shape": [
28
+ 11
29
+ ],
30
+ "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
31
+ "high": "[inf inf inf inf inf inf inf inf inf inf inf]",
32
+ "bounded_below": "[False False False False False False False False False False False]",
33
+ "bounded_above": "[False False False False False False False False False False False]",
34
+ "_np_random": null
35
+ },
36
+ "action_space": {
37
+ ":type:": "<class 'gym.spaces.box.Box'>",
38
+ ":serialized:": "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",
39
+ "dtype": "float32",
40
+ "_shape": [
41
+ 3
42
+ ],
43
+ "low": "[-1. -1. -1.]",
44
+ "high": "[1. 1. 1.]",
45
+ "bounded_below": "[ True True True]",
46
+ "bounded_above": "[ True True True]",
47
+ "_np_random": "RandomState(MT19937)"
48
+ },
49
+ "n_envs": 1,
50
+ "num_timesteps": 1000000,
51
+ "_total_timesteps": 1000000,
52
+ "_num_timesteps_at_start": 0,
53
+ "seed": 0,
54
+ "action_noise": null,
55
+ "start_time": 1675976923779374014,
56
+ "learning_rate": 0.0003,
57
+ "tensorboard_log": "runs/Hopper-v3__tqc__1346000078__1675976919/Hopper-v3",
58
+ "lr_schedule": {
59
+ ":type:": "<class 'function'>",
60
+ ":serialized:": "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"
61
+ },
62
+ "_last_obs": null,
63
+ "_last_episode_starts": {
64
+ ":type:": "<class 'numpy.ndarray'>",
65
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
66
+ },
67
+ "_last_original_obs": {
68
+ ":type:": "<class 'numpy.ndarray'>",
69
+ ":serialized:": "gAWVzQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZYAAAAAAAAAHwBOsRmlvQ/tSdztsb+sj/qs/XpG3DVv4O+di+KP9y/nBQwFhrF6L+aDrScwUD7P2WlTZ+/HwZAWHnEoRzI5T+SPKxekBscQKFNo5E1BRrAAAAAAAAAJMCUjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLC4aUjAFDlHSUUpQu"
70
+ },
71
+ "_episode_num": 2401,
72
+ "use_sde": false,
73
+ "sde_sample_freq": -1,
74
+ "_current_progress_remaining": 0.0,
75
+ "ep_info_buffer": {
76
+ ":type:": "<class 'collections.deque'>",
77
+ ":serialized:": "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"
78
+ },
79
+ "ep_success_buffer": {
80
+ ":type:": "<class 'collections.deque'>",
81
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
82
+ },
83
+ "_n_updates": 990000,
84
+ "buffer_size": 1,
85
+ "batch_size": 256,
86
+ "learning_starts": 10000,
87
+ "tau": 0.005,
88
+ "gamma": 0.99,
89
+ "gradient_steps": 1,
90
+ "optimize_memory_usage": false,
91
+ "replay_buffer_class": {
92
+ ":type:": "<class 'abc.ABCMeta'>",
93
+ ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
94
+ "__module__": "stable_baselines3.common.buffers",
95
+ "__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 ",
96
+ "__init__": "<function ReplayBuffer.__init__ at 0x7fe7060ed5e0>",
97
+ "add": "<function ReplayBuffer.add at 0x7fe7060ed670>",
98
+ "sample": "<function ReplayBuffer.sample at 0x7fe7060ed700>",
99
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x7fe7060ed790>",
100
+ "__abstractmethods__": "frozenset()",
101
+ "_abc_impl": "<_abc._abc_data object at 0x7fe7060ef1c0>"
102
+ },
103
+ "replay_buffer_kwargs": {},
104
+ "train_freq": {
105
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
106
+ ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
107
+ },
108
+ "use_sde_at_warmup": false,
109
+ "target_entropy": -3.0,
110
+ "ent_coef": "auto",
111
+ "target_update_interval": 1,
112
+ "top_quantiles_to_drop_per_net": 5,
113
+ "batch_norm_stats": [],
114
+ "batch_norm_stats_target": []
115
+ }
tqc-Hopper-v3/ent_coef_optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e961a03d615c6119d90417d7029bc5657e3f4e6d161b1281e06ebdb2368f8e
3
+ size 1507
tqc-Hopper-v3/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b8badcebd5324484c920323591f04b8b1e7172a1a4928991622e267ac63b413
3
+ size 1509381
tqc-Hopper-v3/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8877f7dd94b8322b607c878d5655e1f351d30eba302148ed77062f12978271d6
3
+ size 747
tqc-Hopper-v3/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
2
+ - Python: 3.9.12
3
+ - Stable-Baselines3: 1.8.0a6
4
+ - PyTorch: 1.13.1+cu117
5
+ - GPU Enabled: True
6
+ - Numpy: 1.24.1
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:c547c52b2be290c1efbc90e68089d1eca4874bf9017d7934365218745e96da05
3
+ size 80454