Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -79.00 +/- 12.91
+      value: 265.72 +/- 13.29
       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 0x7a0bc8f89750>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a0bc8f897e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a0bc8f89870>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a0bc8f89900>", "_build": "<function ActorCriticPolicy._build at 0x7a0bc8f89990>", "forward": "<function ActorCriticPolicy.forward at 0x7a0bc8f89a20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a0bc8f89ab0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a0bc8f89b40>", "_predict": "<function ActorCriticPolicy._predict at 0x7a0bc8f89bd0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a0bc8f89c60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a0bc8f89cf0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a0bc8f89d80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a0bc8f90800>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 200704, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1717697219038901544, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHOEg71kmYY/fftZvZqgDrxbv6q8ZgWGPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0035199999999999676, "_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": 980, "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": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+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 0x7b8650c21990>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b8650c21a20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b8650c21ab0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b8650c21b40>", "_build": "<function ActorCriticPolicy._build at 0x7b8650c21bd0>", "forward": "<function ActorCriticPolicy.forward at 0x7b8650c21c60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b8650c21cf0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b8650c21d80>", "_predict": "<function ActorCriticPolicy._predict at 0x7b8650c21e10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b8650c21ea0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b8650c21f30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b8650c21fc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b8650bc7dc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718113769731852339, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJpuQ717ypC6C4bqOsAXMTWZcJS5Vu8HugAAgD8AAIA/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": -0.00044800000000000395, "_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": 3908, "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": 1, "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+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:ea71b99ace5b6a86a9e2b3589bfeaa30a0cba0d2daaabbc5e6763ed8ece325e0
-size 147413
+oid sha256:5c8cacc408b628147c4d695b86e8d262bca5b9d7df33b8d814417cafbbce9cb3
+size 147412

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 0x7a0bc8f89750>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a0bc8f897e0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a0bc8f89870>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a0bc8f89900>",
-        "_build": "<function ActorCriticPolicy._build at 0x7a0bc8f89990>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7a0bc8f89a20>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a0bc8f89ab0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a0bc8f89b40>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7a0bc8f89bd0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a0bc8f89c60>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a0bc8f89cf0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a0bc8f89d80>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7b8650c21990>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b8650c21a20>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b8650c21ab0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b8650c21b40>",
+        "_build": "<function ActorCriticPolicy._build at 0x7b8650c21bd0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7b8650c21c60>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b8650c21cf0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b8650c21d80>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7b8650c21e10>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b8650c21ea0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b8650c21f30>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b8650c21fc0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7a0bc8f90800>"
+        "_abc_impl": "<_abc._abc_data object at 0x7b8650bc7dc0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 200704,
-    "_total_timesteps": 200000,
+    "num_timesteps": 1000448,
+    "_total_timesteps": 1000000.0,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1717697219038901544,
+    "start_time": 1718113769731852339,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHOEg71kmYY/fftZvZqgDrxbv6q8ZgWGPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJpuQ717ypC6C4bqOsAXMTWZcJS5Vu8HugAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.0035199999999999676,
+    "_current_progress_remaining": -0.00044800000000000395,
     "_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": 980,
+    "_n_updates": 3908,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -77,14 +77,14 @@
         "_np_random": null
     },
     "n_envs": 1,
-    "n_steps": 2048,
-    "gamma": 0.99,
-    "gae_lambda": 0.95,
-    "ent_coef": 0.0,
+    "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": 10,
+    "n_epochs": 4,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e80f8a9a97a73f153d47d6a8d5bd51796d5488d33a56727aab3ceffcca5042ee
+oid sha256:06b2672194b41d1d43d3a2c9e037b0df09e130c10bf0688a87c3c8c7c03ba028
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d5cab2037b021d96fd824fdaa26e24c45098a1bfdce0b03bda796bb0a50eb22
+oid sha256:0aa42042be6c98acdca45c8e01040d90452fe70e580bb3f738fffe5009b842ce
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": -78.99842166996677, "std_reward": 12.905750522242975, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-06T18:17:38.919616"}
+{"mean_reward": 265.72310027896674, "std_reward": 13.288364906554255, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-11T14:20:53.170811"}