Quentin Gallouédec commited on
Commit
da1035a
1 Parent(s): 7f6dea2

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 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - MountainCar-v0
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: TRPO
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: MountainCar-v0
16
+ type: MountainCar-v0
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -111.60 +/- 9.52
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **TRPO** Agent playing **MountainCar-v0**
25
+ This is a trained model of a **TRPO** agent playing **MountainCar-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 trpo --env MountainCar-v0 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo trpo --env MountainCar-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 trpo --env MountainCar-v0 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo trpo --env MountainCar-v0 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo trpo --env MountainCar-v0 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo trpo --env MountainCar-v0 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('n_critic_updates', 20),
66
+ ('n_envs', 2),
67
+ ('n_steps', 1024),
68
+ ('n_timesteps', 100000.0),
69
+ ('normalize', True),
70
+ ('policy', 'MlpPolicy'),
71
+ ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
72
+ ```
args.yml ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - trpo
4
+ - - device
5
+ - auto
6
+ - - env
7
+ - MountainCar-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
+ - 3932930415
56
+ - - storage
57
+ - null
58
+ - - study_name
59
+ - null
60
+ - - tensorboard_log
61
+ - runs/MountainCar-v0__trpo__3932930415__1670945562
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - n_critic_updates
3
+ - 20
4
+ - - n_envs
5
+ - 2
6
+ - - n_steps
7
+ - 1024
8
+ - - n_timesteps
9
+ - 100000.0
10
+ - - normalize
11
+ - true
12
+ - - policy
13
+ - MlpPolicy
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:bfb616fb2e22bc7ce475f43bd844d871ab292e071313e1c184b888d13a00387b
3
+ size 262159
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -111.6, "std_reward": 9.520504188329523, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T17:12:29.992902"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d32c61fb89f829a14f0a43118ceb9a61ce25d0df765d1b0f161633750a2c022
3
+ size 18131
trpo-MountainCar-v0.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:952b81a3babc0dba308123a60f5f6ab1fc6e90187a98cbc2036130a9346041ba
3
+ size 96884
trpo-MountainCar-v0/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
trpo-MountainCar-v0/data ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
+ "__module__": "stable_baselines3.common.policies",
6
+ "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ",
7
+ "__init__": "<function ActorCriticPolicy.__init__ at 0x7f36c0050d30>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f36c0050dc0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f36c0050e50>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f36c0050ee0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f36c0050f70>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f36c0051040>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f36c00510d0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f36c0051160>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f36c00511f0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f36c0051280>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f36c0051310>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f36c00513a0>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7f36c0052440>"
21
+ },
22
+ "verbose": 1,
23
+ "policy_kwargs": {},
24
+ "observation_space": {
25
+ ":type:": "<class 'gym.spaces.box.Box'>",
26
+ ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
27
+ "dtype": "float32",
28
+ "_shape": [
29
+ 2
30
+ ],
31
+ "low": "[-1.2 -0.07]",
32
+ "high": "[0.6 0.07]",
33
+ "bounded_below": "[ True True]",
34
+ "bounded_above": "[ True True]",
35
+ "_np_random": null
36
+ },
37
+ "action_space": {
38
+ ":type:": "<class 'gym.spaces.discrete.Discrete'>",
39
+ ":serialized:": "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",
40
+ "n": 3,
41
+ "_shape": [],
42
+ "dtype": "int64",
43
+ "_np_random": "RandomState(MT19937)"
44
+ },
45
+ "n_envs": 1,
46
+ "num_timesteps": 100352,
47
+ "_total_timesteps": 100000,
48
+ "_num_timesteps_at_start": 0,
49
+ "seed": 0,
50
+ "action_noise": null,
51
+ "start_time": 1670945565038144226,
52
+ "learning_rate": 0.001,
53
+ "tensorboard_log": "runs/MountainCar-v0__trpo__3932930415__1670945562/MountainCar-v0",
54
+ "lr_schedule": {
55
+ ":type:": "<class 'function'>",
56
+ ":serialized:": "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"
57
+ },
58
+ "_last_obs": null,
59
+ "_last_episode_starts": {
60
+ ":type:": "<class 'numpy.ndarray'>",
61
+ ":serialized:": "gAWVdQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYCAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksChZSMAUOUdJRSlC4="
62
+ },
63
+ "_last_original_obs": {
64
+ ":type:": "<class 'numpy.ndarray'>",
65
+ ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAMk84L4AAAAAk8TwvgAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwJLAoaUjAFDlHSUUpQu"
66
+ },
67
+ "_episode_num": 0,
68
+ "use_sde": false,
69
+ "sde_sample_freq": -1,
70
+ "_current_progress_remaining": -0.0035199999999999676,
71
+ "ep_info_buffer": {
72
+ ":type:": "<class 'collections.deque'>",
73
+ ":serialized:": "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"
74
+ },
75
+ "ep_success_buffer": {
76
+ ":type:": "<class 'collections.deque'>",
77
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
78
+ },
79
+ "_n_updates": 49,
80
+ "n_steps": 1024,
81
+ "gamma": 0.99,
82
+ "gae_lambda": 0.95,
83
+ "ent_coef": 0.0,
84
+ "vf_coef": 0.0,
85
+ "max_grad_norm": 0.0,
86
+ "normalize_advantage": true,
87
+ "batch_size": 128,
88
+ "cg_max_steps": 15,
89
+ "cg_damping": 0.1,
90
+ "line_search_shrinking_factor": 0.8,
91
+ "line_search_max_iter": 10,
92
+ "target_kl": 0.01,
93
+ "n_critic_updates": 20,
94
+ "sub_sampling_factor": 1
95
+ }
trpo-MountainCar-v0/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd6c0813db5ded351c2fdc3f337e0e5782c9e01b7fd3c64a5b7dc157890b1a7
3
+ size 40367
trpo-MountainCar-v0/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb09313841c69070cc6828ef1622d55c755a327bfaf2d029e87e536ad82c02f7
3
+ size 40001
trpo-MountainCar-v0/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
trpo-MountainCar-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
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39369c7bb4321606eb6cb98159f27db076915e8397700491daf9cbdd577f54ca
3
+ size 3969