Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -238.86 +/- 78.73
+      value: 263.74 +/- 21.90
       name: mean_reward
       verified: false
 ---

config.json

@@ -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 0x7be538dd8f70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7be538dd9000>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7be538dd9090>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7be538dd9120>", "_build": "<function ActorCriticPolicy._build at 0x7be538dd91b0>", "forward": "<function ActorCriticPolicy.forward at 0x7be538dd9240>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7be538dd92d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7be538dd9360>", "_predict": "<function ActorCriticPolicy._predict at 0x7be538dd93f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7be538dd9480>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7be538dd9510>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7be538dd95a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7be538f6dfc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 114688, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709853572425559775, "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": -0.1468799999999999, "_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": 48, "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": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"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 0x7d60574e49d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d60574e4a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d60574e4af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d60574e4b80>", "_build": "<function ActorCriticPolicy._build at 0x7d60574e4c10>", "forward": "<function ActorCriticPolicy.forward at 0x7d60574e4ca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d60574e4d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d60574e4dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d60574e4e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d60574e4ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d60574e4f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d60574e5000>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d6057683800>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 14880, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709868590637506686, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAABAyiz61qBk/05PUvpTHsb6y3nI9q+ewvgAAAAAAAAAA2naQPVxbYrqYN8M6xK0Gtj6Ribi9ydu5AAAAAAAAgD9miiI9FFaHulqbLDPxZJstfLcUu/CHv7MAAIA/AACAP2aiCD3DxX66tpTlOOzzMraYa/Q6eqAEuAAAgD8AAIA/JvgWPqChiD9Fy9c9P0v+vv9WCT54leC7AAAAAAAAAADq270+CTNdPyQbpL126sm+btcOPtPwUb4AAAAAAAAAAG1pGb6xwII/W8D8vcWQB79R+hi+vT5ZuwAAAAAAAAAAzcILvnDQ7j7SQd8933umvus70DxNyuK8AAAAAAAAAABDDnO+QUwPvaJYnLvbJyK6zBx5Pv6u8joAAIA/AACAP83imby2VFK8ImXEO7O+dT1xLJW9CC3VugAAgD8AAIA/LUUhPjJbnz9qwI8+DaD5vjxfSD7a9SY+AAAAAAAAAACak1Q9du8/vAYGfLxm/qs73zesPY8Ym7wAAIA/AACAP5rZXTual0I+3qVEPRBza75iaG89BikjPQAAAAAAAAAAzaIFvmAHlz5iQqI9OwSjvkk4mjqHQai8AAAAAAAAAACmeTO+or5zPv0YXD4HS32+wqlTPd3HEz0AAAAAAAAAAGbAurz29R+8dYutvPdg1bzsv4i9PeywvQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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": "2.1.0+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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c8375b03cc237a5ac6ad13fb0e1e99898c6bd634bd68769128cc5c9958f5ae
-size 147963
+oid sha256:dfc2a5cae382496ff146aa4dc1b7c87c81b24f8d57ffbc48fde6269f5c8a48c8
+size 145826

ppo-LunarLander-v2/data

@@ -4,34 +4,34 @@
         ":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 0x7be538dd8f70>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7be538dd9000>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7be538dd9090>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7be538dd9120>",
-        "_build": "<function ActorCriticPolicy._build at 0x7be538dd91b0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7be538dd9240>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7be538dd92d0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7be538dd9360>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7be538dd93f0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7be538dd9480>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7be538dd9510>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7be538dd95a0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7d60574e49d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d60574e4a60>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d60574e4af0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d60574e4b80>",
+        "_build": "<function ActorCriticPolicy._build at 0x7d60574e4c10>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7d60574e4ca0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d60574e4d30>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d60574e4dc0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7d60574e4e50>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d60574e4ee0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d60574e4f70>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d60574e5000>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7be538f6dfc0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7d6057683800>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 114688,
-    "_total_timesteps": 100000,
+    "num_timesteps": 14880,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1709853572425559775,
+    "start_time": 1709868590637506686,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.1468799999999999,
+    "_current_progress_remaining": -0.015808000000000044,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 48,
+    "_n_updates": 248,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a2e9e5301083d35800f2d974c91dc7eb27533b4a06c8937fff67c635822d409
+oid sha256:51c0c22071e56673b3200687d484f55cf28819b9fe8a38d39396901774a2a19e
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92f76c1aa1d1d4b88098a7b5afa09d07dc9316aeffdf1161421b938cbe4b03e0
+oid sha256:7d212cad57de3bc4bbf1a3be3b8dec62ffd0e4bbbee19830d47159e15311fa7c
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": -238.86066409102642, "std_reward": 78.73134588320781, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-07T23:26:23.598916"}
+{"mean_reward": 263.7420192722856, "std_reward": 21.90215650503244, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-08T03:30:31.857972"}