Improve: try 1

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 252.56 +/- 78.95
+      value: 284.15 +/- 20.31
       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 0x7c9ceac868c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c9ceac86950>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c9ceac869e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c9ceac86a70>", "_build": "<function ActorCriticPolicy._build at 0x7c9ceac86b00>", "forward": "<function ActorCriticPolicy.forward at 0x7c9ceac86b90>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c9ceac86c20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c9ceac86cb0>", "_predict": "<function ActorCriticPolicy._predict at 0x7c9ceac86d40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c9ceac86dd0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c9ceac86e60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c9ceac86ef0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c9ceac38b80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 3014656, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1731963692469660836, "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": -0.004885333333333408, "_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": 984, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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 0x7be75be5b2e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7be75be5b370>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7be75be5b400>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7be75be5b490>", "_build": "<function ActorCriticPolicy._build at 0x7be75be5b520>", "forward": "<function ActorCriticPolicy.forward at 0x7be75be5b5b0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7be75be5b640>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7be75be5b6d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7be75be5b760>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7be75be5b7f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7be75be5b880>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7be75be5b910>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7be6fe3fdb00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 524288, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1733690752119049762, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAANPXq76PiDo/+TcbviYZI7+LFeG+WVA8PQAAAAAAAAAAGvkYvgWEJT4XEZM+gnKyvuVIMr0vSss9AAAAAAAAAACalYm9V619POQ7lj6ncpW+1uOOvMUg2D0AAAAAAAAAADP7cT3uYY28Si0hvqYekD27EaY9kdsbvAAAgD8AAIA/mtGEO6BjrD953EM9PoUKvzF+gjyVk/g9AAAAAAAAAABAlIG9Pe8CP3Kt4TzGG+++QVXVvDitxLwAAAAAAAAAADa1VL6TScs+8l88Pm+33b6WAh6+Yl0MPQAAAAAAAAAAALwcvuZ0KD9Qn6k9QhX5vsNP+71rwlE9AAAAAAAAAACmCpU9n1qNPkKerL6P4/C+eDASvu2KDL4AAAAAAAAAAJr/Srz3V7E/d5Mev4boE78cA0M89/m+PQAAAAAAAAAAoDMyPivAWD/FKdy7kUUIvwADsD5IcfW9AAAAAAAAAAAz4kc+Uuy9u94KcjpVI8K3qZg8vYoYkLkAAAAAAAAAABpfN77WTe4+4vDSPR69Ar/LyFC+XgHLPQAAAAAAAAAAs/hZPSv3rz4fYoe+kaL5vllz7L22bFi9AAAAAAAAAADNDIW7rpepujDQTLy3JJA8Gd0ROzWOer0AAIA/AACAP/MEqb1C74w+AiGJPWbtzr59grq97rGfPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.04857599999999995, "_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": 160, "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": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.02, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "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 Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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 sha256:91cd86da2676cdace438b5bdf32b6e2671dcf1e8730b04a3be925ba5d765ad94
-size 148072
+oid sha256:5db17af11a79c22ec63f2bbec2f3384c2ab384db0d54622a4ee57628a9c72926
+size 147891

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 0x7c9ceac868c0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c9ceac86950>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c9ceac869e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c9ceac86a70>",
-        "_build": "<function ActorCriticPolicy._build at 0x7c9ceac86b00>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7c9ceac86b90>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c9ceac86c20>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c9ceac86cb0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7c9ceac86d40>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c9ceac86dd0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c9ceac86e60>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c9ceac86ef0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7be75be5b2e0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7be75be5b370>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7be75be5b400>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7be75be5b490>",
+        "_build": "<function ActorCriticPolicy._build at 0x7be75be5b520>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7be75be5b5b0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7be75be5b640>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7be75be5b6d0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7be75be5b760>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7be75be5b7f0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7be75be5b880>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7be75be5b910>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7c9ceac38b80>"
+        "_abc_impl": "<_abc._abc_data object at 0x7be6fe3fdb00>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 3014656,
-    "_total_timesteps": 3000000,
+    "num_timesteps": 524288,
+    "_total_timesteps": 500000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1731963692469660836,
+    "start_time": 1733690752119049762,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAOCexb5Ob6w+WDqYPtKnGL8x1wG/m/raPQAAAAAAAAAA6/ahvjTJlT7QGOI+qUrIvokOYr6IJWk+AAAAAAAAAACaK9A89gRuuvk2BjzRQga0f8SQO32bgrMAAAAAAAAAADPPDD2sxl0/kyqkvGBXEr/TFaA9lyaCvQAAAAAAAAAAmulouyngV7oLUVe3dVlksuUUULh9S3w2AACAPwAAgD8zTzY+2i8VP57Lyr0vheK+cNl2PtKz9r0AAAAAAAAAAJpnCL0b1Dk/IgwCvoXyEr91BHy8Z/cXvQAAAAAAAAAAuo9RPo34Bb1boKo7c+xKums7b774aCq7AACAPwAAAADmCm89HfKIP471DD4wLgy/xR1WPmxOCD4AAAAAAAAAAJqaWj32xBe6yxhxOcW7nzSDx2K5ke6OuAAAAAAAAAAAmmj1PDZSULz2nwI6zrFxPZuFpz3S4Vy7AACAPwAAgD+ay6u927iBvOgvvz7KWgW+Li3nvdLo2b4AAIA/AACAPxqaW70f4M67FTPHPSayhTxlJyI926ZivQAAAAAAAAAAwDEdPg92VrzmUXo74xAEumOUvL17P+K6AACAPwAAgD9aHvk92+0uPz1AeL16+P6+hGZnPhbz0r0AAAAAAAAAAFq2oD6+s5w/UeOnPnGJAL/x4hA/pxOFugAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
+        ":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": -0.004885333333333408,
+    "_current_progress_remaining": -0.04857599999999995,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWV5wsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHCE79ycTamMAWyUS8iMAXSUR0CtMwLjo6jndX2UKGgGR0ByVHzK9wm3aAdL5GgIR0CtMyt70Fr3dX2UKGgGR0ByTVnyup0faAdL2GgIR0CtM3pSR8txdX2UKGgGR0BzOOVeKKpDaAdLyWgIR0CtNCqnvUjLdX2UKGgGR0BngzV6NVBEaAdN6ANoCEdArTRLVe8f3nV9lChoBkdAceNmelKsdWgHS8hoCEdArTRVS/CZW3V9lChoBkdAb6+nDR+jM2gHS7RoCEdArTRUBbOeKHV9lChoBkdAcX36pHZsbmgHS9RoCEdArTSA3vQWvnV9lChoBkdAc44aiblRxmgHS9ZoCEdArTSfFNtZWHV9lChoBkdAcfuZQYUFjmgHS9doCEdArTS5qh11XHV9lChoBkdAcfeitJWeYmgHS9FoCEdArTTfmknCwnV9lChoBkdAcZ6VAiV0LmgHS75oCEdArTTtpItlI3V9lChoBkdAcK2nH/95yGgHS7loCEdArTVPbEgnt3V9lChoBkdAcLBOKO1fFGgHS+FoCEdArTVfxhDw6XV9lChoBkdAcpS0r9VFQWgHTSMBaAhHQK01i/h2nsN1fZQoaAZHQHLPwBT4tYloB0vnaAhHQK01pt3wCr91fZQoaAZHQHFwcENe+mFoB0vFaAhHQK02fpyIYWN1fZQoaAZHQHKLt92HLzRoB0vPaAhHQK02p5wfhdd1fZQoaAZHQHISkQbuMMtoB0vCaAhHQK02tHe7+UB1fZQoaAZHQHJjh4lhPTJoB0vgaAhHQK02tCtRvWJ1fZQoaAZHQHErn3QD3dtoB0vhaAhHQK024haC+UR1fZQoaAZHQHF6Zi/fwZxoB0vHaAhHQK02536hxo91fZQoaAZHQHH5HcHnln1oB0u6aAhHQK03A5jH4oJ1fZQoaAZHQG8AJgssg+1oB0vTaAhHQK03KnP3SKF1fZQoaAZHQHJuTQJHAh1oB0uwaAhHQK03WfV7QcB1fZQoaAZHQHEfax1PnCBoB0vLaAhHQK03u4x1xKh1fZQoaAZHQG4N41YQrc1oB0vDaAhHQK0304jrzGx1fZQoaAZHQG68+vpyIYZoB0vgaAhHQK04TzCk43p1fZQoaAZHQFBr1/DtPYZoB0uvaAhHQK04ngaWHDd1fZQoaAZHQHHlJTAFgUloB0vIaAhHQK05LTJhfBx1fZQoaAZHQHKv0mUnogVoB0vOaAhHQK05QJ8fFJh1fZQoaAZHQHBqF4cFQl9oB0vGaAhHQK05XjcVQAN1fZQoaAZHQG9L+u/1xsFoB0vGaAhHQK05gbADaGp1fZQoaAZHQHOGAzk6tDFoB0vsaAhHQK05mxJul411fZQoaAZHQHFcd7ngYP5oB0vNaAhHQK05vL2YfGN1fZQoaAZHQHIUrKq4pc5oB0u9aAhHQK05v+2mYSh1fZQoaAZHQGX/p0OmR/5oB03oA2gIR0CtOcQ66reZdX2UKGgGR0BzypBLPD51aAdL6GgIR0CtOcmTs6aLdX2UKGgGR0Bw4WxSpBHDaAdLvGgIR0CtRQPFvQ4TdX2UKGgGR0BvQ4aBI4EPaAdLx2gIR0CtRQ00elsQdX2UKGgGR0BxVWcBltj1aAdN2AFoCEdArUVh8MNMG3V9lChoBkdAcmwztkWhy2gHS7loCEdArUVmkSElFHV9lChoBkdAb2fQBxPweGgHS8JoCEdArUXG/N7jUHV9lChoBkdAZapK15Sm7GgHTegDaAhHQK1F3qVQhwF1fZQoaAZHQHGHow/PgNxoB0u4aAhHQK1GHWwu/UR1fZQoaAZHQHEdXsw+MZRoB0u6aAhHQK1GMwMYuTR1fZQoaAZHQHB6rSVnmJZoB0u4aAhHQK1GXtmcvuh1fZQoaAZHQHEz91hb4ahoB0uyaAhHQK1GZD3ueBh1fZQoaAZHQHHb1B+nZTRoB0uyaAhHQK1GhlaKUFB1fZQoaAZHQHQUXgLqlgtoB0vLaAhHQK1GxoxpL291fZQoaAZHQHNTtszl90BoB0vWaAhHQK1G5C1qnFZ1fZQoaAZHQHECXNHH3lFoB0vXaAhHQK1G8YgJTl11fZQoaAZHQHGg91yNn5BoB0vFaAhHQK1HLJr+Hah1fZQoaAZHQHMOVW0Z3s5oB0vSaAhHQK1HSQ+UyHp1fZQoaAZHQHHWg+IMz/JoB0vHaAhHQK1HkjwhGH51fZQoaAZHQHMONFfAsTZoB0v1aAhHQK1IHnBciW51fZQoaAZHQHNiKg2606ZoB0vbaAhHQK1IO0rsjVx1fZQoaAZHQG8Hx+BpYcNoB0vOaAhHQK1IdEORT0h1fZQoaAZHQHKEt30PH1hoB0vlaAhHQK1IdlCkXUJ1fZQoaAZHQHEX4rjHXEtoB0u+aAhHQK1IlAY51eV1fZQoaAZHQHIUiaEzwc5oB0vdaAhHQK1Iub0e2eB1fZQoaAZHQHE7OEdvKlpoB0vTaAhHQK1Izp7CzkZ1fZQoaAZHQHLo3ZXdTHdoB0u/aAhHQK1JIyeqaPV1fZQoaAZHQG6NcWCVbA1oB0vJaAhHQK1JJLrX18N1fZQoaAZHQHGHXc580DVoB0vBaAhHQK1JOUMXrMV1fZQoaAZHQHJibo0Q9RtoB0vMaAhHQK1Juj+rELp1fZQoaAZHQGPW3ZPEbYNoB03oA2gIR0CtShCay8jBdX2UKGgGR0BznlFRYRukaAdL3GgIR0CtSkNVzZHvdX2UKGgGR0ByWFqxkd3jaAdLrWgIR0CtSpLc0tROdX2UKGgGR0Bw9xooNNJwaAdLzGgIR0CtSrxOtW+5dX2UKGgGR0ByGvYBeXzEaAdL42gIR0CtSuipFTegdX2UKGgGR0BwYPms/6fraAdLvWgIR0CtSuk3S8aodX2UKGgGR0ByORwhnrY5aAdLzWgIR0CtSv4s3AEddX2UKGgGR0BvfIQz1sciaAdLxmgIR0CtSz/HHWBjdX2UKGgGR0By4VS1maphaAdL12gIR0CtS19dE9dNdX2UKGgGR0Byd0DQqqffaAdL1WgIR0CtS8k7W/ahdX2UKGgGR0BxIGl9BrvcaAdL0GgIR0CtS9Htv4ucdX2UKGgGR0BzRNKFqSHNaAdL8WgIR0CtTCYYJmdzdX2UKGgGR0Bygo2MsH0LaAdLyGgIR0CtTEBoEjgRdX2UKGgGR0BwD1VcUucuaAdLt2gIR0CtTFjUd7v5dX2UKGgGR0BzxtJlJ6IFaAdLwGgIR0CtTKW5hBqsdX2UKGgGR0BvtEYXO4XoaAdLvWgIR0CtTOwCCBf8dX2UKGgGR0ByMx1fVqetaAdLyWgIR0CtTTp0fYBedX2UKGgGR0Bx/yeumrKeaAdLw2gIR0CtTWt1p0wKdX2UKGgGR0BxFg8QqZtvaAdL02gIR0CtTYvPszEadX2UKGgGR0Bv8Wuq3mV8aAdLv2gIR0CtTcihFmWddX2UKGgGR0BzCIbXHzYmaAdL/mgIR0CtTiDFqBVddX2UKGgGR0BwrxcMVk+YaAdL5GgIR0CtTij2JzkqdX2UKGgGR0ByMYOc2BJ7aAdLwWgIR0CtTkn1OCXhdX2UKGgGR0BwfJzXBguzaAdLzmgIR0CtTuokzGgjdX2UKGgGR0BuyUlqrR0EaAdLymgIR0CtTvfXwsoVdX2UKGgGR0BzDrMKTjebaAdL12gIR0CtUAscp9ZzdX2UKGgGR0ByU42Hck+paAdL12gIR0CtUFknkT6BdX2UKGgGR0Bul9qk/KQraAdLwWgIR0CtULp6po9LdX2UKGgGR0Bygp1Oj7AMaAdL32gIR0CtUNLt3OfNdX2UKGgGR0ByRWRKYiPiaAdL3mgIR0CtUQUEovzwdX2UKGgGR0BirOY4Qz1saAdN6ANoCEdArVELHAAQx3V9lChoBkdAccFZYgaFVWgHS65oCEdArVEc2rGR3nV9lChoBkdAcre8r7O3UmgHS81oCEdArVEqnLq2SnV9lChoBkdAcmU+ocaOxWgHS8toCEdArVF4h4dIXnVlLg=="
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 984,
+    "_n_updates": 160,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -69,7 +69,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -77,14 +77,14 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "n_steps": 1024,
+    "n_steps": 2048,
     "gamma": 0.999,
     "gae_lambda": 0.98,
-    "ent_coef": 0.01,
+    "ent_coef": 0.02,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 4,
+    "batch_size": 128,
+    "n_epochs": 10,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":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:f95f3c7aa6e6708c81e20456312a28289d51b58a5797a6dfe9fbdb395ea9e4ce
-size 88490
+oid sha256:26501d45a9e38475d619c401fe17e79d2ee750f24b0b17238d0dbcb4f0aab42a
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8d5dfdbaecaaf2a83d0a8401b750358484f83fd4f5937201a1e3a58b6999c0e
+oid sha256:d4f8ad58123a516cd65c9f9e63ed249858785a9d4db3ad432da5fe8e0d75ebb8
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": 252.5586963, "std_reward": 78.94656550466013, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-18T21:36:35.102589"}
+{"mean_reward": 284.1455391, "std_reward": 20.312639310854124, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-08T20:55:44.269316"}