jinghuanHuggingface commited on
Commit
8df3c94
·
verified ·
1 Parent(s): 71a12f8

Upload PPO LunarLander-v2 trained agent

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
- value: 222.66 +/- 23.91
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: 243.94 +/- 21.56
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 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 0x7eb748647010>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eb7486470a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eb748647130>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eb7486471c0>", "_build": "<function ActorCriticPolicy._build at 0x7eb748647250>", "forward": "<function ActorCriticPolicy.forward at 0x7eb7486472e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eb748647370>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eb748647400>", "_predict": "<function ActorCriticPolicy._predict at 0x7eb748647490>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eb748647520>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eb7486475b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eb748647640>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7eb748abd340>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1705418574560819903, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
 
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 0x7cf0d8255900>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cf0d8255990>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cf0d8255a20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cf0d8255ab0>", "_build": "<function ActorCriticPolicy._build at 0x7cf0d8255b40>", "forward": "<function ActorCriticPolicy.forward at 0x7cf0d8255bd0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cf0d8255c60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cf0d8255cf0>", "_predict": "<function ActorCriticPolicy._predict at 0x7cf0d8255d80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cf0d8255e10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cf0d8255ea0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cf0d8255f30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cf0d83ebe80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1714376862487867536, "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": 124, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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": 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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
ppo-LunarLander-v2.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c4d1b242ee2b86a27ec7cb0366fdc06c0b89f5dfb104b616c9670fa82bb74ad
3
- size 148056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb47e8a8f778f576b2ac0a31fc2de3c1eb36adaa22c192a55e2615dbd1607ef1
3
+ size 148088
ppo-LunarLander-v2/data CHANGED
@@ -4,20 +4,20 @@
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 0x7eb748647010>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eb7486470a0>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eb748647130>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eb7486471c0>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7eb748647250>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7eb7486472e0>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eb748647370>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eb748647400>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7eb748647490>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eb748647520>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eb7486475b0>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eb748647640>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x7eb748abd340>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
@@ -26,12 +26,12 @@
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
- "start_time": 1705418574560819903,
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'>",
@@ -45,16 +45,16 @@
45
  "_stats_window_size": 100,
46
  "ep_info_buffer": {
47
  ":type:": "<class 'collections.deque'>",
48
- ":serialized:": "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"
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]",
@@ -69,7 +69,7 @@
69
  },
70
  "action_space": {
71
  ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
72
- ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
73
  "n": "4",
74
  "start": "0",
75
  "_shape": [],
@@ -77,7 +77,7 @@
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,
 
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 0x7cf0d8255900>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cf0d8255990>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cf0d8255a20>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cf0d8255ab0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7cf0d8255b40>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7cf0d8255bd0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cf0d8255c60>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cf0d8255cf0>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7cf0d8255d80>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cf0d8255e10>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cf0d8255ea0>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cf0d8255f30>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7cf0d83ebe80>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
 
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
+ "start_time": 1714376862487867536,
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'>",
 
45
  "_stats_window_size": 100,
46
  "ep_info_buffer": {
47
  ":type:": "<class 'collections.deque'>",
48
+ ":serialized:": "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"
49
  },
50
  "ep_success_buffer": {
51
  ":type:": "<class 'collections.deque'>",
52
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
  },
54
+ "_n_updates": 124,
55
  "observation_space": {
56
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
+ ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
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]",
 
69
  },
70
  "action_space": {
71
  ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
72
+ ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
73
  "n": "4",
74
  "start": "0",
75
  "_shape": [],
 
77
  "_np_random": null
78
  },
79
  "n_envs": 16,
80
+ "n_steps": 2048,
81
  "gamma": 0.999,
82
  "gae_lambda": 0.98,
83
  "ent_coef": 0.01,
ppo-LunarLander-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b99d1bc5128f9c4114fee7b616cc68b9fbf5824bef9a7f2680c56f20512c9cc
3
  size 88362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44aa6000ee84e337cbac9c8831f01f028dedd190df91ff47fd4826b0538732b5
3
  size 88362
ppo-LunarLander-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7c633009686a0d778238cfb69f9bc11ba21adc3311920b288cb56484e04d5a4
3
  size 43762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee73a238f104f4c20c23b0bc7ab23b2f6e855026e97cac755e1ce86ede069c9
3
  size 43762
ppo-LunarLander-v2/system_info.txt CHANGED
@@ -1,9 +1,9 @@
1
  - OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.0.0a5
4
- - PyTorch: 2.1.0+cu121
5
  - GPU Enabled: True
6
- - Numpy: 1.23.5
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.28.1
9
  - OpenAI Gym: 0.25.2
 
1
  - OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.0.0a5
4
+ - PyTorch: 2.2.1+cu121
5
  - GPU Enabled: True
6
+ - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.28.1
9
  - OpenAI Gym: 0.25.2
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 222.65800596951743, "std_reward": 23.90768128169906, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-16T15:51:56.032928"}
 
1
+ {"mean_reward": 243.9434352269615, "std_reward": 21.55696205915535, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-29T08:08:10.996027"}