nzdb70 commited on
Commit
8c7ba00
1 Parent(s): 5ffc0f3

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: 253.10 +/- 17.32
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: 259.50 +/- 24.26
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 0x799414c80790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x799414c80820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x799414c808b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x799414c80940>", "_build": "<function ActorCriticPolicy._build at 0x799414c809d0>", "forward": "<function ActorCriticPolicy.forward at 0x799414c80a60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x799414c80af0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x799414c80b80>", "_predict": "<function ActorCriticPolicy._predict at 0x799414c80c10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x799414c80ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x799414c80d30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x799414c80dc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x799414c787c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711707945299737637, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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-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"}}
 
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 0x784dd2de4a60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x784dd2de4af0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x784dd2de4b80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x784dd2de4c10>", "_build": "<function ActorCriticPolicy._build at 0x784dd2de4ca0>", "forward": "<function ActorCriticPolicy.forward at 0x784dd2de4d30>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x784dd2de4dc0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x784dd2de4e50>", "_predict": "<function ActorCriticPolicy._predict at 0x784dd2de4ee0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x784dd2de4f70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x784dd2de5000>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x784dd2de5090>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x784dd2f6b140>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711957997907209641, "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": 252, "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": 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-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:bd3c0c1284b69443101cb167cd8bb01159f7395c04e5e2bcc9ae515798e30771
3
- size 148084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f667e1d36044e03fccc614b5d9ce3b8746489e65e69d7bd363bfa92944839fd8
3
+ size 148072
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 0x799414c80790>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x799414c80820>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x799414c808b0>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x799414c80940>",
11
- "_build": "<function ActorCriticPolicy._build at 0x799414c809d0>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x799414c80a60>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x799414c80af0>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x799414c80b80>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x799414c80c10>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x799414c80ca0>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x799414c80d30>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x799414c80dc0>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x799414c787c0>"
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": 1711707945299737637,
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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",
 
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 0x784dd2de4a60>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x784dd2de4af0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x784dd2de4b80>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x784dd2de4c10>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x784dd2de4ca0>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x784dd2de4d30>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x784dd2de4dc0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x784dd2de4e50>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x784dd2de4ee0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x784dd2de4f70>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x784dd2de5000>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x784dd2de5090>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x784dd2f6b140>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
 
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
+ "start_time": 1711957997907209641,
30
  "learning_rate": 0.0003,
31
  "tensorboard_log": null,
32
  "_last_obs": {
33
  ":type:": "<class 'numpy.ndarray'>",
34
+ ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAPPRAL6kBGe72JgrvLBupbp5F7M8tjyOOwAAgD8AAIA/AI9EvdCDvT5bBD89o20tvqOIYz0k0BG9AAAAAAAAAAAQtZC+9bHqPiyVnD275o6+dFKvvB9pwT0AAAAAAAAAAGYoRD7XKX48sCF+OtfQvzhPiw0+3riiuQAAgD8AAIA/s5gUPrhyr7s5+4M68yEAuNUiJL0iU6S5AACAPwAAgD8a2Uy9e5ikulKKdTm+BX00XWfuOuQIjbgAAIA/AACAP7NVVL32PF266ZYDtEtLla73uZS4CoS1MwAAgD8AAIA/GqmxvVyvBboaNFC6gjAlNeL6JztmvnY5AACAPwAAgD/exbi+o1BNP43k+r7Ahd++36KXvhZ6ZL4AAAAAAAAAAPNroL1i9L4+9qEGvCJEW76ZZ029cKNdvAAAAAAAAAAA2uCUPcMdfrq8fwM5zQMtsvD+Dbuq7ha4AACAPwAAgD8zAai9FMKcusprjrnVriezJzX5uiX+oTgAAIA/AACAP7p1Cr5SRo67PU7xuw8fALqhnMM86BvbOgAAgD8AAIA/AKRHPsTI7T4KEte9xo6qvl7A6zwQo0Y9AAAAAAAAAADmlB497TdcP62W1bz0xam+eFe+PKsHEzwAAAAAAAAAAABTi73X01m5dg2TOXcf+bLxno67nnuvuAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
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": 252,
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:aca877835c9f8f8d333a7c8cee28cb0646dba30799e373b9c5b1daffdcb1ca59
3
  size 88362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285ca20434fdc5a4d9a00084b19710b1fba29ddb85a1f3153b42d2f55b831e56
3
  size 88362
ppo-LunarLander-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1957db646604053e9bcf7a8cce95f2e36c36ee7e2eb326dfddcd7648ec6005d4
3
  size 43762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98cf6673cf244e7d00c7e5999cdfb714836192480beceb298f745452808dd92
3
  size 43762
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 253.0994838014223, "std_reward": 17.324817317440633, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-29T11:07:59.134622"}
 
1
+ {"mean_reward": 259.5023308, "std_reward": 24.264614128084183, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-01T08:18:53.674131"}