araffin commited on
Commit
40e156f
1 Parent(s): d4a4295

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 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - Swimmer-v3
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: PPO
10
+ results:
11
+ - metrics:
12
+ - type: mean_reward
13
+ value: 281.78 +/- 11.86
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: Swimmer-v3
20
+ type: Swimmer-v3
21
+ ---
22
+
23
+ # **PPO** Agent playing **Swimmer-v3**
24
+ This is a trained model of a **PPO** agent playing **Swimmer-v3**
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 ppo --env Swimmer-v3 -orga sb3 -f logs/
41
+ python enjoy.py --algo ppo --env Swimmer-v3 -f logs/
42
+ ```
43
+
44
+ ## Training (with the RL Zoo)
45
+ ```
46
+ python train.py --algo ppo --env Swimmer-v3 -f logs/
47
+ # Upload the model and generate video (when possible)
48
+ python -m utils.push_to_hub --algo ppo --env Swimmer-v3 -f logs/ -orga sb3
49
+ ```
50
+
51
+ ## Hyperparameters
52
+ ```python
53
+ OrderedDict([('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
54
+ ('gamma', 0.9999),
55
+ ('n_timesteps', 1000000.0),
56
+ ('normalize', True),
57
+ ('policy', 'MlpPolicy'),
58
+ ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
59
+ ```
args.yml ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - ppo
4
+ - - env
5
+ - Swimmer-v3
6
+ - - env_kwargs
7
+ - null
8
+ - - eval_episodes
9
+ - 20
10
+ - - eval_freq
11
+ - 10000
12
+ - - gym_packages
13
+ - []
14
+ - - hyperparams
15
+ - null
16
+ - - log_folder
17
+ - logs/
18
+ - - log_interval
19
+ - 10
20
+ - - n_eval_envs
21
+ - 5
22
+ - - n_evaluations
23
+ - 20
24
+ - - n_jobs
25
+ - 1
26
+ - - n_startup_trials
27
+ - 10
28
+ - - n_timesteps
29
+ - -1
30
+ - - n_trials
31
+ - 10
32
+ - - no_optim_plots
33
+ - false
34
+ - - num_threads
35
+ - 2
36
+ - - optimization_log_path
37
+ - null
38
+ - - optimize_hyperparameters
39
+ - false
40
+ - - pruner
41
+ - median
42
+ - - sampler
43
+ - tpe
44
+ - - save_freq
45
+ - -1
46
+ - - save_replay_buffer
47
+ - false
48
+ - - seed
49
+ - 594371
50
+ - - storage
51
+ - null
52
+ - - study_name
53
+ - null
54
+ - - tensorboard_log
55
+ - ''
56
+ - - trained_agent
57
+ - ''
58
+ - - truncate_last_trajectory
59
+ - true
60
+ - - uuid
61
+ - true
62
+ - - vec_env
63
+ - dummy
64
+ - - verbose
65
+ - 1
config.yml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - env_wrapper
3
+ - sb3_contrib.common.wrappers.TimeFeatureWrapper
4
+ - - gamma
5
+ - 0.9999
6
+ - - n_timesteps
7
+ - 1000000.0
8
+ - - normalize
9
+ - true
10
+ - - policy
11
+ - MlpPolicy
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
ppo-Swimmer-v3.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4de3596420b347673a24c302789b2598db625bc843a0a98825b07a7813fb30
3
+ size 148668
ppo-Swimmer-v3/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.5.1a8
ppo-Swimmer-v3/data ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
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 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()`` 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 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 0x7f00482f9950>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f00482f99e0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f00482f9a70>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f00482f9b00>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f00482f9b90>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f00482f9c20>",
13
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f00482f9cb0>",
14
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f00482f9d40>",
15
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f00482f9dd0>",
16
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f00482f9e60>",
17
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f00482f9ef0>",
18
+ "__abstractmethods__": "frozenset()",
19
+ "_abc_impl": "<_abc_data object at 0x7f004834a840>"
20
+ },
21
+ "verbose": 1,
22
+ "policy_kwargs": {},
23
+ "observation_space": {
24
+ ":type:": "<class 'gym.spaces.box.Box'>",
25
+ ":serialized:": "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",
26
+ "dtype": "float32",
27
+ "low": "[-inf -inf -inf -inf -inf -inf -inf -inf 0.]",
28
+ "high": "[inf inf inf inf inf inf inf inf 1.]",
29
+ "bounded_below": "[False False False False False False False False True]",
30
+ "bounded_above": "[False False False False False False False False True]",
31
+ "_np_random": null,
32
+ "_shape": [
33
+ 9
34
+ ]
35
+ },
36
+ "action_space": {
37
+ ":type:": "<class 'gym.spaces.box.Box'>",
38
+ ":serialized:": "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",
39
+ "dtype": "float32",
40
+ "low": "[-1. -1.]",
41
+ "high": "[1. 1.]",
42
+ "bounded_below": "[ True True]",
43
+ "bounded_above": "[ True True]",
44
+ "_np_random": "RandomState(MT19937)",
45
+ "_shape": [
46
+ 2
47
+ ]
48
+ },
49
+ "n_envs": 1,
50
+ "num_timesteps": 1001472,
51
+ "_total_timesteps": 1000000,
52
+ "_num_timesteps_at_start": 0,
53
+ "seed": 0,
54
+ "action_noise": null,
55
+ "start_time": 1635497829.4608934,
56
+ "learning_rate": 0.0003,
57
+ "tensorboard_log": null,
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:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
66
+ },
67
+ "_last_original_obs": {
68
+ ":type:": "<class 'numpy.ndarray'>",
69
+ ":serialized:": "gASVrgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLCYaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMkbPgbvGzDUT3eJ789NR0AvXQrBj0LFWo9qM7hvJGD+bwAAIA/lHSUYi4="
70
+ },
71
+ "_episode_num": 0,
72
+ "use_sde": false,
73
+ "sde_sample_freq": -1,
74
+ "_current_progress_remaining": -0.0014719999999999178,
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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
82
+ },
83
+ "_n_updates": 4890,
84
+ "n_steps": 2048,
85
+ "gamma": 0.9999,
86
+ "gae_lambda": 0.95,
87
+ "ent_coef": 0.0,
88
+ "vf_coef": 0.5,
89
+ "max_grad_norm": 0.5,
90
+ "batch_size": 64,
91
+ "n_epochs": 10,
92
+ "clip_range": {
93
+ ":type:": "<class 'function'>",
94
+ ":serialized:": "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"
95
+ },
96
+ "clip_range_vf": null,
97
+ "normalize_advantage": true,
98
+ "target_kl": null
99
+ }
ppo-Swimmer-v3/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81708a7edbfd0f2fc764c343100b6ac8fa5d98fdd67605076a38abd3035136bc
3
+ size 85399
ppo-Swimmer-v3/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47a375678257f635141848d0d3e9a2c2e043450251c9620fa92ad256affac384
3
+ size 43518
ppo-Swimmer-v3/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
ppo-Swimmer-v3/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
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59df8219ce13dcf6462731d2a2dcc73aec74ab71ba22327f1952cd217a60ac34
3
+ size 1399979
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 281.7792699, "std_reward": 11.86036112635292, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T13:54:38.770471"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcde9ca629d66d4540cbc624776a7be208de1ae0dd996473cf5b9b12982fb3f2
3
+ size 61686
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a373c53839bd87085268455c1f23cea8e281b0cc265812c57520aa2ce00a43ec
3
+ size 4600