Quentin Gallouédec commited on
Commit
c117902
1 Parent(s): 513dfc4

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 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - MountainCarContinuous-v0
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: MountainCarContinuous-v0
16
+ type: MountainCarContinuous-v0
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 90.28 +/- 0.49
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **TQC** Agent playing **MountainCarContinuous-v0**
25
+ This is a trained model of a **TQC** agent playing **MountainCarContinuous-v0**
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 MountainCarContinuous-v0 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo tqc --env MountainCarContinuous-v0 -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 MountainCarContinuous-v0 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo tqc --env MountainCarContinuous-v0 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo tqc --env MountainCarContinuous-v0 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo tqc --env MountainCarContinuous-v0 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 512),
66
+ ('buffer_size', 50000),
67
+ ('ent_coef', 0.1),
68
+ ('gamma', 0.9999),
69
+ ('gradient_steps', 32),
70
+ ('learning_rate', 0.0003),
71
+ ('learning_starts', 0),
72
+ ('n_timesteps', 50000.0),
73
+ ('policy', 'MlpPolicy'),
74
+ ('policy_kwargs', 'dict(log_std_init=-3.67, net_arch=[64, 64])'),
75
+ ('tau', 0.01),
76
+ ('train_freq', 32),
77
+ ('use_sde', True),
78
+ ('normalize', False)])
79
+ ```
args.yml ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - tqc
4
+ - - device
5
+ - auto
6
+ - - env
7
+ - MountainCarContinuous-v0
8
+ - - env_kwargs
9
+ - null
10
+ - - eval_episodes
11
+ - 20
12
+ - - eval_freq
13
+ - 25000
14
+ - - gym_packages
15
+ - []
16
+ - - hyperparams
17
+ - null
18
+ - - log_folder
19
+ - logs
20
+ - - log_interval
21
+ - -1
22
+ - - max_total_trials
23
+ - null
24
+ - - n_eval_envs
25
+ - 5
26
+ - - n_evaluations
27
+ - null
28
+ - - n_jobs
29
+ - 1
30
+ - - n_startup_trials
31
+ - 10
32
+ - - n_timesteps
33
+ - -1
34
+ - - n_trials
35
+ - 500
36
+ - - no_optim_plots
37
+ - false
38
+ - - num_threads
39
+ - -1
40
+ - - optimization_log_path
41
+ - null
42
+ - - optimize_hyperparameters
43
+ - false
44
+ - - progress
45
+ - false
46
+ - - pruner
47
+ - median
48
+ - - sampler
49
+ - tpe
50
+ - - save_freq
51
+ - -1
52
+ - - save_replay_buffer
53
+ - false
54
+ - - seed
55
+ - 2181305313
56
+ - - storage
57
+ - null
58
+ - - study_name
59
+ - null
60
+ - - tensorboard_log
61
+ - runs/MountainCarContinuous-v0__tqc__2181305313__1670944334
62
+ - - track
63
+ - true
64
+ - - trained_agent
65
+ - ''
66
+ - - truncate_last_trajectory
67
+ - true
68
+ - - uuid
69
+ - false
70
+ - - vec_env
71
+ - dummy
72
+ - - verbose
73
+ - 1
74
+ - - wandb_entity
75
+ - openrlbenchmark
76
+ - - wandb_project_name
77
+ - sb3
78
+ - - yaml_file
79
+ - null
config.yml ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 512
4
+ - - buffer_size
5
+ - 50000
6
+ - - ent_coef
7
+ - 0.1
8
+ - - gamma
9
+ - 0.9999
10
+ - - gradient_steps
11
+ - 32
12
+ - - learning_rate
13
+ - 0.0003
14
+ - - learning_starts
15
+ - 0
16
+ - - n_timesteps
17
+ - 50000.0
18
+ - - policy
19
+ - MlpPolicy
20
+ - - policy_kwargs
21
+ - dict(log_std_init=-3.67, net_arch=[64, 64])
22
+ - - tau
23
+ - 0.01
24
+ - - train_freq
25
+ - 32
26
+ - - use_sde
27
+ - 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 sha256:240c7652a9ab9f5e9e3af96bf0b862856799adcd2f419f9b0439f87632d1f112
3
+ size 264456
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 90.28224399999999, "std_reward": 0.4911590969144292, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T16:39:07.970835"}
tqc-MountainCarContinuous-v0.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bc60f984e92ff41af92317056e801bd6989e12890393f8a801cc981945277b3
3
+ size 292940
tqc-MountainCarContinuous-v0/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
tqc-MountainCarContinuous-v0/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11c13371a2462186d0199028d1d29823ffd55581f7c4674a9fe23a41870b7554
3
+ size 41702
tqc-MountainCarContinuous-v0/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4954f266fdc604c5a4f349072c23d6a45579d811b02d19ea83c18cd60952eed
3
+ size 106169
tqc-MountainCarContinuous-v0/data ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 0x7f9caad234c0>",
8
+ "_build": "<function TQCPolicy._build at 0x7f9caad23550>",
9
+ "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f9caad235e0>",
10
+ "reset_noise": "<function TQCPolicy.reset_noise at 0x7f9caad23670>",
11
+ "make_actor": "<function TQCPolicy.make_actor at 0x7f9caad23700>",
12
+ "make_critic": "<function TQCPolicy.make_critic at 0x7f9caad23790>",
13
+ "forward": "<function TQCPolicy.forward at 0x7f9caad23820>",
14
+ "_predict": "<function TQCPolicy._predict at 0x7f9caad238b0>",
15
+ "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f9caad23940>",
16
+ "__abstractmethods__": "frozenset()",
17
+ "_abc_impl": "<_abc._abc_data object at 0x7f9caad24100>"
18
+ },
19
+ "verbose": 1,
20
+ "policy_kwargs": {
21
+ "log_std_init": -3.67,
22
+ "net_arch": [
23
+ 64,
24
+ 64
25
+ ],
26
+ "use_sde": true
27
+ },
28
+ "observation_space": {
29
+ ":type:": "<class 'gym.spaces.box.Box'>",
30
+ ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
31
+ "dtype": "float32",
32
+ "_shape": [
33
+ 2
34
+ ],
35
+ "low": "[-1.2 -0.07]",
36
+ "high": "[0.6 0.07]",
37
+ "bounded_below": "[ True True]",
38
+ "bounded_above": "[ True True]",
39
+ "_np_random": null
40
+ },
41
+ "action_space": {
42
+ ":type:": "<class 'gym.spaces.box.Box'>",
43
+ ":serialized:": "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",
44
+ "dtype": "float32",
45
+ "_shape": [
46
+ 1
47
+ ],
48
+ "low": "[-1.]",
49
+ "high": "[1.]",
50
+ "bounded_below": "[ True]",
51
+ "bounded_above": "[ True]",
52
+ "_np_random": "RandomState(MT19937)"
53
+ },
54
+ "n_envs": 1,
55
+ "num_timesteps": 50016,
56
+ "_total_timesteps": 50000,
57
+ "_num_timesteps_at_start": 0,
58
+ "seed": 0,
59
+ "action_noise": null,
60
+ "start_time": 1670944337082280945,
61
+ "learning_rate": {
62
+ ":type:": "<class 'function'>",
63
+ ":serialized:": "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"
64
+ },
65
+ "tensorboard_log": "runs/MountainCarContinuous-v0__tqc__2181305313__1670944334/MountainCarContinuous-v0",
66
+ "lr_schedule": {
67
+ ":type:": "<class 'function'>",
68
+ ":serialized:": "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"
69
+ },
70
+ "_last_obs": null,
71
+ "_last_episode_starts": {
72
+ ":type:": "<class 'numpy.ndarray'>",
73
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
74
+ },
75
+ "_last_original_obs": {
76
+ ":type:": "<class 'numpy.ndarray'>",
77
+ ":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAADqtmz6FBHy8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwKGlIwBQ5R0lFKULg=="
78
+ },
79
+ "_episode_num": 337,
80
+ "use_sde": true,
81
+ "sde_sample_freq": -1,
82
+ "_current_progress_remaining": -0.000320000000000098,
83
+ "ep_info_buffer": {
84
+ ":type:": "<class 'collections.deque'>",
85
+ ":serialized:": "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"
86
+ },
87
+ "ep_success_buffer": {
88
+ ":type:": "<class 'collections.deque'>",
89
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
90
+ },
91
+ "_n_updates": 50016,
92
+ "buffer_size": 1,
93
+ "batch_size": 512,
94
+ "learning_starts": 0,
95
+ "tau": 0.01,
96
+ "gamma": 0.9999,
97
+ "gradient_steps": 32,
98
+ "optimize_memory_usage": false,
99
+ "replay_buffer_class": {
100
+ ":type:": "<class 'abc.ABCMeta'>",
101
+ ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
102
+ "__module__": "stable_baselines3.common.buffers",
103
+ "__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 ",
104
+ "__init__": "<function ReplayBuffer.__init__ at 0x7f9cab1aa430>",
105
+ "add": "<function ReplayBuffer.add at 0x7f9cab1aa4c0>",
106
+ "sample": "<function ReplayBuffer.sample at 0x7f9cab1aa550>",
107
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x7f9cab1aa5e0>",
108
+ "__abstractmethods__": "frozenset()",
109
+ "_abc_impl": "<_abc._abc_data object at 0x7f9cab1a1800>"
110
+ },
111
+ "replay_buffer_kwargs": {},
112
+ "train_freq": {
113
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
114
+ ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLIGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
115
+ },
116
+ "use_sde_at_warmup": false,
117
+ "target_entropy": -1.0,
118
+ "log_ent_coef": null,
119
+ "ent_coef": 0.1,
120
+ "target_update_interval": 1,
121
+ "ent_coef_optimizer": null,
122
+ "top_quantiles_to_drop_per_net": 2,
123
+ "batch_norm_stats": [],
124
+ "batch_norm_stats_target": []
125
+ }
tqc-MountainCarContinuous-v0/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e513b04b79af5abc0e8d6ab3589ec38879157c5f4803bb636198ac1dc45a0acb
3
+ size 125000
tqc-MountainCarContinuous-v0/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39440af5158e3fb47ecc525e9d329ecbd7c856bf70fd565c749cc2c45263e188
3
+ size 747
tqc-MountainCarContinuous-v0/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 sha256:5a466df12cdb2a43f2f66218e8eebbf9d4a9a8d99c5a0e79f24c5b06eff7c6b4
3
+ size 10226