jaygdesai commited on
Commit
be22ba1
1 Parent(s): 258ebd4

Upload default 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: 253.08 +/- 64.67
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: 266.06 +/- 22.80
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 0x7b8c7669caf0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b8c7669cb80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b8c7669cc10>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b8c7669cca0>", "_build": "<function ActorCriticPolicy._build at 0x7b8c7669cd30>", "forward": "<function ActorCriticPolicy.forward at 0x7b8c7669cdc0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b8c7669ce50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b8c7669cee0>", "_predict": "<function ActorCriticPolicy._predict at 0x7b8c7669cf70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b8c7669d000>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b8c7669d090>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b8c7669d120>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b8c77406680>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689850439528903935, "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-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 0x7b821f9137f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b821f913880>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b821f913910>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b821f9139a0>", "_build": "<function ActorCriticPolicy._build at 0x7b821f913a30>", "forward": "<function ActorCriticPolicy.forward at 0x7b821f913ac0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b821f913b50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b821f913be0>", "_predict": "<function ActorCriticPolicy._predict at 0x7b821f913c70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b821f913d00>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b821f913d90>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b821f913e20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b821f918c40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689879938229134892, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "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-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "False", "Numpy": "1.22.4", "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 sha256:64412343d3a7d3eaf4c86df01d254b6a594d30b542869a3c6b22bc40a83ef89b
3
- size 146749
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f92d271a9dc0ae6af9fbe8d8bdbaacdc488d9bc7374a42147b9f18d147ef0de1
3
+ size 146221
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 0x7b8c7669caf0>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b8c7669cb80>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b8c7669cc10>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b8c7669cca0>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7b8c7669cd30>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7b8c7669cdc0>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b8c7669ce50>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b8c7669cee0>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7b8c7669cf70>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b8c7669d000>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b8c7669d090>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b8c7669d120>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x7b8c77406680>"
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": 1689850439528903935,
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'>",
@@ -45,13 +45,13 @@
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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",
@@ -77,13 +77,13 @@
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'>",
 
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 0x7b821f9137f0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b821f913880>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b821f913910>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b821f9139a0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7b821f913a30>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7b821f913ac0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b821f913b50>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b821f913be0>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7b821f913c70>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b821f913d00>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b821f913d90>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b821f913e20>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7b821f918c40>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
 
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
+ "start_time": 1689879938229134892,
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:": "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",
 
77
  "_np_random": null
78
  },
79
  "n_envs": 16,
80
+ "n_steps": 2048,
81
+ "gamma": 0.99,
82
  "gae_lambda": 0.98,
83
  "ent_coef": 0.01,
84
  "vf_coef": 0.5,
85
  "max_grad_norm": 0.5,
86
+ "batch_size": 32,
87
  "n_epochs": 4,
88
  "clip_range": {
89
  ":type:": "<class 'function'>",
ppo-LunarLander-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:354ae42681bd013c7618c07a314c902789f297a24deb6adc6c2cdbe9298f83f0
3
- size 87929
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aef0077dfc17fb08b0c931c923364f9e6e70806c56dd5fc2e13b588030d65cf
3
+ size 87545
ppo-LunarLander-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:561c95773255243fb45e63b3892dcda3ce0381edefdb0678ff1beac288921935
3
- size 43329
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a1e890076c7c044e348d5472f200850d124b1dfc1747a801ca10bc592ed17f9
3
+ size 43201
ppo-LunarLander-v2/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.6
3
  - Stable-Baselines3: 2.0.0a5
4
  - PyTorch: 2.0.1+cu118
5
- - GPU Enabled: True
6
  - Numpy: 1.22.4
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.28.1
 
2
  - Python: 3.10.6
3
  - Stable-Baselines3: 2.0.0a5
4
  - PyTorch: 2.0.1+cu118
5
+ - GPU Enabled: False
6
  - Numpy: 1.22.4
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.28.1
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 253.0764921873576, "std_reward": 64.66902305593767, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-20T11:17:22.196809"}
 
1
+ {"mean_reward": 266.0587871645439, "std_reward": 22.795864734918478, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-20T20:32:35.362203"}