nomsgadded commited on
Commit
da0857c
1 Parent(s): 535d235

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: -26.85 +/- 21.19
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: 247.89 +/- 48.43
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 0x7fd6704ea9d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd6704eaa60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd6704eaaf0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd6704eab80>", "_build": "<function ActorCriticPolicy._build at 0x7fd6704eac10>", "forward": "<function ActorCriticPolicy.forward at 0x7fd6704eaca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd6704ead30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd6704eadc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd6704eae50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd6704eaee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd6704eaf70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd6704ee040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fd670566d80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 200192, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1696215712230671915, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAPn5b68Png9OhUyv2Rbt7wc3Au76ZCtvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0009600000000000719, "_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": 6256, "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": 1, "n_steps": 256, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 1024, "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-6.2.0-33-generic-x86_64-with-glibc2.17 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Sep 7 10:33:52 UTC 2", "Python": "3.8.18", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1"}}
 
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 0x7ff3848c19d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff3848c1a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff3848c1af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff3848c1b80>", "_build": "<function ActorCriticPolicy._build at 0x7ff3848c1c10>", "forward": "<function ActorCriticPolicy.forward at 0x7ff3848c1ca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff3848c1d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff3848c1dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff3848c1e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff3848c1ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff3848c1f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff3848c5040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7ff38493cde0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 4000000, "_total_timesteps": 4000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1696217199586082317, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABqZlr2Pziy66oQWOAKKfTOAV2E7dtsvtwAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_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": 109376, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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": 1, "n_steps": 256, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 1024, "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-6.2.0-33-generic-x86_64-with-glibc2.17 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Sep 7 10:33:52 UTC 2", "Python": "3.8.18", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1"}}
ppo-LunarLander-v2.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f59f514a0fdf412f641185b02a807de21008472981c7483178207e79ad735951
3
- size 146180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde657d583ada84b5887d64902085da411af51a90f24a0ffd2f1b7c31e205ae4
3
+ size 146121
ppo-LunarLander-v2/data CHANGED
@@ -4,34 +4,34 @@
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 0x7fd6704ea9d0>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd6704eaa60>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd6704eaaf0>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd6704eab80>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7fd6704eac10>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7fd6704eaca0>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd6704ead30>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd6704eadc0>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7fd6704eae50>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd6704eaee0>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd6704eaf70>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd6704ee040>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc_data object at 0x7fd670566d80>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
24
- "num_timesteps": 200192,
25
- "_total_timesteps": 200000,
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
- "start_time": 1696215712230671915,
30
  "learning_rate": 0.0003,
31
  "tensorboard_log": null,
32
  "_last_obs": {
33
  ":type:": "<class 'numpy.ndarray'>",
34
- ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAPn5b68Png9OhUyv2Rbt7wc3Au76ZCtvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
35
  },
36
  "_last_episode_starts": {
37
  ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
41
  "_episode_num": 0,
42
  "use_sde": false,
43
  "sde_sample_freq": -1,
44
- "_current_progress_remaining": -0.0009600000000000719,
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": 6256,
55
  "observation_space": {
56
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
  ":serialized:": "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",
 
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 0x7ff3848c19d0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff3848c1a60>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff3848c1af0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff3848c1b80>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7ff3848c1c10>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7ff3848c1ca0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff3848c1d30>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff3848c1dc0>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7ff3848c1e50>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff3848c1ee0>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff3848c1f70>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff3848c5040>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc_data object at 0x7ff38493cde0>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
24
+ "num_timesteps": 4000000,
25
+ "_total_timesteps": 4000000,
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
+ "start_time": 1696217199586082317,
30
  "learning_rate": 0.0003,
31
  "tensorboard_log": null,
32
  "_last_obs": {
33
  ":type:": "<class 'numpy.ndarray'>",
34
+ ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABqZlr2Pziy66oQWOAKKfTOAV2E7dtsvtwAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
35
  },
36
  "_last_episode_starts": {
37
  ":type:": "<class 'numpy.ndarray'>",
 
41
  "_episode_num": 0,
42
  "use_sde": false,
43
  "sde_sample_freq": -1,
44
+ "_current_progress_remaining": 0.0,
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": 109376,
55
  "observation_space": {
56
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
  ":serialized:": "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",
ppo-LunarLander-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62557e7f42981f9de1ed86e59ad33bbe0d88d69c83035c998f9ab31129e03567
3
  size 87929
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c6ac366ce12fdf6f7defa8e0ab99f2fe8cb527108c65fe33368bb1b0270acae
3
  size 87929
ppo-LunarLander-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe7b29694eaa8c0430d63d48e8d62c8027d2405756a552eb6e25023903a121c3
3
  size 43329
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd4fb967f284b59cd3a78cf6ea93a714a714448584d205732e62a1ef0dfc8114
3
  size 43329
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -26.851714699999995, "std_reward": 21.188723367898113, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-02T11:03:23.466494"}
 
1
+ {"mean_reward": 247.89459870000002, "std_reward": 48.434235065612015, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-02T11:53:40.948229"}