bastienm commited on
Commit
99793a6
1 Parent(s): b6a4599

Add ppo-LunarLander-v2 RL model

Browse files
BastienM_ppo-LunarLander-v2.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215c8a9b5ef02b295e0c6a6c65891b63f12087fd6a7606614b19d32c9cbf8f8a
3
+ size 146751
BastienM_ppo-LunarLander-v2/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.0.0a5
BastienM_ppo-LunarLander-v2/data ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 0x7ff38025f9a0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff38025fa30>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff38025fac0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff38025fb50>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7ff38025fbe0>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7ff38025fc70>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff38025fd00>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff38025fd90>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7ff38025fe20>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff38025feb0>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff38025ff40>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff38026c040>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7ff380268300>"
21
+ },
22
+ "verbose": 1,
23
+ "policy_kwargs": {},
24
+ "num_timesteps": 1015808,
25
+ "_total_timesteps": 1000000,
26
+ "_num_timesteps_at_start": 0,
27
+ "seed": null,
28
+ "action_noise": null,
29
+ "start_time": 1683972365971118027,
30
+ "learning_rate": 0.0003,
31
+ "tensorboard_log": null,
32
+ "_last_obs": {
33
+ ":type:": "<class 'numpy.ndarray'>",
34
+ ":serialized:": "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"
35
+ },
36
+ "_last_episode_starts": {
37
+ ":type:": "<class 'numpy.ndarray'>",
38
+ ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
39
+ },
40
+ "_last_original_obs": null,
41
+ "_episode_num": 0,
42
+ "use_sde": false,
43
+ "sde_sample_freq": -1,
44
+ "_current_progress_remaining": -0.015808000000000044,
45
+ "_stats_window_size": 100,
46
+ "ep_info_buffer": {
47
+ ":type:": "<class 'collections.deque'>",
48
+ ":serialized:": "gAWVPgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQG6gYku6EraMAWyUTaYBjAF0lEdAmNLfr0J4S3V9lChoBkdAcV+B9kSVW2gHTUIDaAhHQJjX8pG4I8h1fZQoaAZHQGGfOtfXwspoB03oA2gIR0CY3vABkqc3dX2UKGgGR0BlP2O+7Dl6aAdN6ANoCEdAmOZaePJaJXV9lChoBkdAYX62LpA2RGgHTegDaAhHQJjoU95hScd1fZQoaAZHQG8Nm7z06HVoB02OAmgIR0CY7cxtYSxrdX2UKGgGR0BgADrxAjY7aAdN6ANoCEdAmO5gRsdkrnV9lChoBkdAZ5RZnL7oCGgHTegDaAhHQJj0FmOEM9d1fZQoaAZHQHHgd8JD3M9oB01NAWgIR0CY9CZi/fwadX2UKGgGR0BjcrdYW+GoaAdN6ANoCEdAmPVunhsImnV9lChoBkdAZQJzkp7TlWgHTegDaAhHQJj2HUhFEzB1fZQoaAZHQGHn7xusLfFoB03oA2gIR0CY9huZ1FH8dX2UKGgGR0BkwRd+ocaPaAdN6ANoCEdAmP5JvP1L8XV9lChoBkdAYBYMPSUkfWgHTegDaAhHQJkBF3kgfU51fZQoaAZHQGYhNN8E3bVoB03oA2gIR0CZA6nmaH9FdX2UKGgGR0BeRL0Fr2xqaAdN6ANoCEdAmQ20CRwIdHV9lChoBkdAcVq3PzFuN2gHTZIBaAhHQJkQbxSYPXl1fZQoaAZHQF8DucMEzO5oB03oA2gIR0CZEKMDfWMCdX2UKGgGR0BwB4PCl7+laAdN3gNoCEdAmSGUi+tbLXV9lChoBkdAXPruNPxhD2gHTegDaAhHQJkmpMZgogF1fZQoaAZHQG9uxO+IuXhoB036AmgIR0CZMhDQqqffdX2UKGgGR0BlXzfgrH2iaAdN6ANoCEdAmTMG5MDfWXV9lChoBkdAXyrS7Xg9/2gHTegDaAhHQJk1C2phnap1fZQoaAZHQG/+SKvV3EBoB01qAmgIR0CZNhKPn0TUdX2UKGgGR0Bl5qZ+hGpdaAdN6ANoCEdAmTrrXlKbrnV9lChoBkdAaPoyNXHR1GgHTegDaAhHQJk7kh/y5I91fZQoaAZHQGIxrELpiZxoB03oA2gIR0CZQnDeCTUzdX2UKGgGR0Bkcw/X5FgEaAdN6ANoCEdAmUQyMcZLqXV9lChoBkdAZQcHY6GQCGgHTegDaAhHQJlFFt3wCr91fZQoaAZHQFrfBvJiiItoB03oA2gIR0CZTCjps41hdX2UKGgGR0BlYd50KZ2IaAdN6ANoCEdAmVBsC9ytFXV9lChoBkdAcFjzSCvovGgHTWADaAhHQJlVZ+BpYcN1fZQoaAZHQHGXOLNwBHVoB02SA2gIR0CZVvXWvr4WdX2UKGgGR0Bs2o+dK/VRaAdNSAJoCEdAmVePRVp9JHV9lChoBkdAZE4kk8ifQWgHTegDaAhHQJlY6JFb3XZ1fZQoaAZHQGNYTRx95QhoB03oA2gIR0CZW7kOI68ydX2UKGgGR0Bybu9g4OtoaAdN1wNoCEdAmXJCYb83uXV9lChoBkdAbnDufEn9emgHTVoDaAhHQJl4jPE87p51fZQoaAZHQGy+gpjMFEBoB02HAmgIR0CZepiPyTY/dX2UKGgGR0BxpAIjW07baAdNZgNoCEdAmX5aEWZZ0XV9lChoBkdAYfSao/A0sWgHTegDaAhHQJmFYH1OCXh1fZQoaAZHQHGI6eGwiaBoB00tAWgIR0CZhy+hXbM5dX2UKGgGR0Bw3JMCcPOIaAdN2ANoCEdAmYnoj4YaYXV9lChoBkdAb9Ksrd30PGgHTWMDaAhHQJmKKCtihFp1fZQoaAZHQGPG/JNj9XNoB03oA2gIR0CZilMOf/WEdX2UKGgGR0BvV+NipeeGaAdNSwJoCEdAmYy8s189fXV9lChoBkdAcUiDGcWj5GgHTf8BaAhHQJmNdlXiiqR1fZQoaAZHQHB2YrWiDdxoB01FAWgIR0CZjlSZ0CA+dX2UKGgGR0Bkq42n889waAdN6ANoCEdAmZFW+K0laHV9lChoBkdAbnfg9eQdS2gHTbgCaAhHQJmSaSZBsyl1fZQoaAZHQHCf5Sm65G1oB005A2gIR0CZkryWzF/AdX2UKGgGR0AvMlhw2l2vaAdNCgFoCEdAmZcX9rGipXV9lChoBkdAXeW2a2F36mgHTegDaAhHQJmXdN9H+ZR1fZQoaAZHQEl9ivxH5JtoB0vsaAhHQJmX86V+qip1fZQoaAZHQGWQt0FKTStoB03oA2gIR0CZoJF3Y+SsdX2UKGgGR0ByMHp8neBQaAdNHAFoCEdAmaGTOgQHzHV9lChoBkdAYyhPD50r9WgHTegDaAhHQJmkXZXdTHd1fZQoaAZHQG5aAAAAAABoB02lAWgIR0CZpItCRfWudX2UKGgGR0BvPcWj4593aAdNwAFoCEdAmaULXL/0d3V9lChoBkdAboP3M6ij+WgHTRUCaAhHQJml/ChvitJ1fZQoaAZHQG3uumBOHnFoB00jAmgIR0CZptroGIKudX2UKGgGR0BthHT9bX6JaAdNowFoCEdAmaekSZjQRnV9lChoBkdAcwSVRDTjN2gHTW0CaAhHQJmn6k56t1Z1fZQoaAZHQG6C544ZMtdoB03SAWgIR0CZv/ZZB9kSdX2UKGgGR0A6T4+KTB69aAdL8mgIR0CZwZpWFN+LdX2UKGgGR0BxMdEx7AtWaAdNsQFoCEdAmcNtHH3lCHV9lChoBkdAcTkvkRzzVmgHTcIBaAhHQJnDeZUkv9N1fZQoaAZHQG+KSydFvydoB00UAWgIR0CZw9nb7CSBdX2UKGgGR0Bh52QSzw+daAdN6ANoCEdAmcPj2OAAhnV9lChoBkdATyLB68g6l2gHTQcBaAhHQJnFLc580DV1fZQoaAZHQBLRKtga3qloB00PAWgIR0CZxaZUDMePdX2UKGgGR0BRc+OS4e90aAdL9mgIR0CZxnZ1V5rydX2UKGgGR0BrfvduYQaraAdNBgJoCEdAmcZ5dnkDIXV9lChoBkdAZazqyGBWgmgHTegDaAhHQJnGy9AX2uh1fZQoaAZHQEiobfgrH2hoB00dAWgIR0CZyEoXsPatdX2UKGgGR0BxkE7uDzy0aAdNxgNoCEdAmcmFLBbfQHV9lChoBkdANR9UGVzIWGgHS/VoCEdAmcr7xAjY7XV9lChoBkdAU1xZ8rqdH2gHS+RoCEdAmcvioCMglnV9lChoBkdAbVUKUFB6bGgHTdABaAhHQJnNCZSeiBZ1fZQoaAZHQG9c27FsHjZoB02nAWgIR0CZzdrsjVx0dX2UKGgGR0Bv3GHHmzSkaAdN6QFoCEdAmc7Zy6tknXV9lChoBkdAcmBmT1TR6WgHTUIBaAhHQJnPxMVUMod1fZQoaAZHQHBEQJ5VwP1oB01RAWgIR0CZ0sQQ+UyIdX2UKGgGR0BwVDh99c8laAdNEwFoCEdAmdNrgTAWSHV9lChoBkdAceCh6By0bGgHTZcBaAhHQJnT642CNCJ1fZQoaAZHQHBVOG47Rv5oB02mAWgIR0CZ1ICqp97XdX2UKGgGR0A2/hUBGQS0aAdL7WgIR0CZ1vlnyup0dX2UKGgGR0BvQ8gKWszVaAdN3QFoCEdAmdgfZM+NcXV9lChoBkdAb2UA4n4O+mgHTXQBaAhHQJnY3LX+VC51fZQoaAZHQG+XtzS1E3NoB037AWgIR0CZ2p39aUzLdX2UKGgGR0BSwehTOxB3aAdNIQFoCEdAmdvSKaXrt3V9lChoBkdAcyRmOU+s5mgHTZsBaAhHQJnb+h7E5yV1fZQoaAZHQHGYPrB0p3JoB01EAmgIR0CZ3Z0IC2c8dX2UKGgGR0BwgqS2Yv38aAdNZQFoCEdAmd2s/UvwmXV9lChoBkdAcVSjIJZ4fWgHTaMBaAhHQJnfIPczqKR1fZQoaAZHQHE6/TG5tnBoB00hAmgIR0CZ4stsvZh8dX2UKGgGR0ByevbzshPkaAdNvAJoCEdAmeONNzr/sHV9lChoBkdAcMVcrAgxJ2gHTUABaAhHQJnm6HP/rB11fZQoaAZHQG8XTmwJPZZoB02vAWgIR0CZ53fNzKcNdX2UKGgGR0BwK0gow22oaAdNHAFoCEdAmehsdo3713VlLg=="
49
+ },
50
+ "ep_success_buffer": {
51
+ ":type:": "<class 'collections.deque'>",
52
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
+ },
54
+ "_n_updates": 248,
55
+ "observation_space": {
56
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
+ ":serialized:": "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",
58
+ "dtype": "float32",
59
+ "bounded_below": "[ True True True True True True True True]",
60
+ "bounded_above": "[ True True True True True True True True]",
61
+ "_shape": [
62
+ 8
63
+ ],
64
+ "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
65
+ "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
66
+ "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
67
+ "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
68
+ "_np_random": null
69
+ },
70
+ "action_space": {
71
+ ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
72
+ ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
73
+ "n": "4",
74
+ "start": "0",
75
+ "_shape": [],
76
+ "dtype": "int64",
77
+ "_np_random": null
78
+ },
79
+ "n_envs": 16,
80
+ "n_steps": 1024,
81
+ "gamma": 0.999,
82
+ "gae_lambda": 0.98,
83
+ "ent_coef": 0.01,
84
+ "vf_coef": 0.5,
85
+ "max_grad_norm": 0.5,
86
+ "batch_size": 64,
87
+ "n_epochs": 4,
88
+ "clip_range": {
89
+ ":type:": "<class 'function'>",
90
+ ":serialized:": "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"
91
+ },
92
+ "clip_range_vf": null,
93
+ "normalize_advantage": true,
94
+ "target_kl": null,
95
+ "lr_schedule": {
96
+ ":type:": "<class 'function'>",
97
+ ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
98
+ }
99
+ }
BastienM_ppo-LunarLander-v2/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9e388f4e5a273ca29a036ae6f6da4d5853a30ae4d440c945bb56de7a0f05337
3
+ size 87929
BastienM_ppo-LunarLander-v2/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1749b2b59e283b967e3d4b95e13909406f5aa47f5b7d2779c286741f7a6e24b
3
+ size 43329
BastienM_ppo-LunarLander-v2/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
BastienM_ppo-LunarLander-v2/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
2
+ - Python: 3.10.11
3
+ - Stable-Baselines3: 2.0.0a5
4
+ - PyTorch: 2.0.0+cu118
5
+ - GPU Enabled: True
6
+ - Numpy: 1.22.4
7
+ - Cloudpickle: 2.2.1
8
+ - Gymnasium: 0.28.1
9
+ - OpenAI Gym: 0.25.2
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - LunarLander-v2
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: PPO
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: LunarLander-v2
16
+ type: LunarLander-v2
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 263.46 +/- 20.86
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **PPO** Agent playing **LunarLander-v2**
25
+ This is a trained model of a **PPO** agent playing **LunarLander-v2**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
27
+
28
+ ## Usage (with Stable-baselines3)
29
+ TODO: Add your code
30
+
31
+
32
+ ```python
33
+ from stable_baselines3 import ...
34
+ from huggingface_sb3 import load_from_hub
35
+
36
+ ...
37
+ ```
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7ff38025f9a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff38025fa30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff38025fac0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff38025fb50>", "_build": "<function ActorCriticPolicy._build at 0x7ff38025fbe0>", "forward": "<function ActorCriticPolicy.forward at 0x7ff38025fc70>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff38025fd00>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff38025fd90>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff38025fe20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff38025feb0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff38025ff40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff38026c040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff380268300>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1683972365971118027, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
replay.mp4 ADDED
Binary file (187 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 263.4596487157874, "std_reward": 20.85524902315297, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-13T10:47:03.012839"}