ppo model for ppo-LunarLander-v2 for the Unit 1 of Huggingface Deep RL
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +28 -28
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 278.91 +/- 14.75
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +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 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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f7abb7fbc10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7abb7fbca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7abb7fbd30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7abb7fbdc0>", "_build": "<function ActorCriticPolicy._build at 0x7f7abb7fbe50>", "forward": "<function ActorCriticPolicy.forward at 0x7f7abb7fbee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7abb7fbf70>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7abb780040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7abb7800d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7abb780160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7abb7801f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f7abb7fa450>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 32, "num_timesteps": 368000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652272866.0520153, "learning_rate": 0.0, "tensorboard_log": "logs", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQQAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYABAAAAAAAAACWczz21Fi69O4Gs+0+aq687Hs6yqebMwAAgD8AAIA/DcoPvmtLJj+jgkU++8JZvzhAqL5xz6M+AAAAAAAAAAAA9oM8yrukPwrI1j1PIBu/VYuOPXC8Vj4AAAAAAAAAADOtiz3ogZM9aqyMvjEQ4b5zBEs9BaP4vQAAAAAAAAAADfOcvcQIwj8BnpC+vKy6vZT1QL0bHXG+AAAAAAAAAAD7loS+6UVPP1vYYz4T2EW/U+UEvwIyiz4AAAAAAAAAAM2xhbw0uMu8UPJWPmUc9Dwd1i89WyyMPQAAgD8AAIA/s5y8PTbcsz9KQfQ+RLp2vqQS7j37X3Y+AAAAAAAAAABm2ls8nBM6vD1rdj27Clc9A2GHveanpDsAAIA/AACAP1N3ET4k39k+/3PCvRUGN7/Ssos+cxcgvgAAAAAAAAAAU9sivgS/hD7+DOY+UHYhv67fPL4S3cA+AAAAAAAAAADm6DQ+KRmePw7h1j5/yDO/IV7UPslVtT4AAAAAAAAAAM2sILqfxL67tBvGO8m3AD1OVWo8yyozPAAAgD8AAIA/AICCOkhFirrKDlS0CzGfL23mJLtm6YczAACAPwAAgD/g4SO+SWmUPiVD+D4KTTe/QMQHviP52z4AAAAAAAAAAJofhTxSHOK7SpsFuxN1yDw83Z88j2q1OgAAgD8AAIA/ZiujvMV4gz/KC4+9vDiCv1Mjeb1Pir29AAAAAAAAAADjD2G+DW8pPxwAiz4n2Ua/TvHSvivIeD4AAAAAAAAAAE1UlL0RpkU/YnHjvFTGUr/1VoG+sh9NPQAAAAAAAAAAQDouvmjcrz/SeQG/TyfovhXL8b6ahtC+AAAAAAAAAADmp249bu7JPepqVb5fNQC/Ot+4PQ6pHL4AAAAAAAAAAGamNrtIx6S6hbxRMpwh5LCMYsW6xuSmsgAAgD8AAIA/mvGSO1Kg67vut2W7umMwPMAwP736IBk9AACAPwAAgD8AsCs8PW4uu2a+gjovB7Q8A14pvMuTmT0AAIA/AACAPzNA47yMbBM+vmdvPcaaAr+SxpW9he6hPQAAAAAAAAAAc2ZEvncCST9nKyC8ZwIfvzlsBb+hYRw+AAAAAAAAAACanaq718s9uzZffLye45k8JTWkvGaXgz0AAIA/AACAPzMc/bzuiLq8TVViPt2Ymr3tWiO9stIHvgAAgD8AAIA/M+fQO8NwDbw2q2c9MmcDvcZx47xj+OS+AACAPwAAgD8t45A+gG4wP3ZSA77vzUe/OM7gPjLim74AAAAAAAAAAM2kbzuFJ4G7zJQVvkzSsTzcWb48tO6WvQAAgD8AAIA/zchOvSc3LT9+j2E7g+RbvzCd/71q5kQ9AAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSyBLCIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.67232, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 19344, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 256, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
|
|
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 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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fc66c423820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc66c4238b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc66c423940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc66c4239d0>", "_build": "<function ActorCriticPolicy._build at 0x7fc66c423a60>", "forward": "<function ActorCriticPolicy.forward at 0x7fc66c423af0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc66c423b80>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc66c423c10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc66c423ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc66c423d30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc66c423dc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fc66c41e6c0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 212992, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1672622457211411126, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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": -0.0649599999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 600, "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, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb6ba459de560622cc5c9ea61b42db414ae8ed8d51908ccd30522a513049d1c8
|
3 |
+
size 147218
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,19 +4,19 @@
|
|
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 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
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -41,52 +41,52 @@
|
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
-
"n_envs":
|
45 |
-
"num_timesteps":
|
46 |
-
"_total_timesteps":
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
-
"learning_rate": 0.
|
52 |
-
"tensorboard_log":
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
-
":serialized:": "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
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
-
":serialized:": "
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": 0.
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
-
"n_steps":
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
-
"batch_size":
|
86 |
-
"n_epochs":
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
-
":serialized:": "
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
|
|
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 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 0x7fc66c423820>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc66c4238b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc66c423940>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc66c4239d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fc66c423a60>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fc66c423af0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc66c423b80>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fc66c423c10>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc66c423ca0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc66c423d30>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc66c423dc0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fc66c41e6c0>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 212992,
|
46 |
+
"_total_timesteps": 200000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1672622457211411126,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.0649599999999999,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 600,
|
79 |
+
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f6b80654f0a41f637ec6183f15df106fe207c3047d02182894495d11709be5c
|
3 |
+
size 88057
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43201
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9d5cc32c04bc4796758eaf986433e75cd557225646f3c5a48993542140ddef5
|
3 |
size 43201
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 278.912623676356, "std_reward": 14.749468192802812, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T01:36:56.765551"}
|