Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 21.97 +/- 119.43
+      value: 36.25 +/- 106.75
       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 0x7f97f7dc3ba0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f97f7dc3c40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f97f7dc3ce0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f97f7dc3d80>", "_build": "<function ActorCriticPolicy._build at 0x7f97f7dc3e20>", "forward": "<function ActorCriticPolicy.forward at 0x7f97f7dc3ec0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f97f7dc3f60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f97f7dcc040>", "_predict": "<function ActorCriticPolicy._predict at 0x7f97f7dcc0e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f97f7dcc180>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f97f7dcc220>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f97f7dcc2c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f97f7dafe00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713173381150121153, "learning_rate": 0.0003, "tensorboard_log": "logs", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADDXgT44w6o9FGerPbOksb28HTE9WyBtPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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, "n_steps": 1024, "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:": "gAWV7wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjGUvaG9tZS9zYWluaTUvbWluaWNvbmRhMy9lbnZzL2hmX3JsX2Vudi9saWIvcHl0aG9uMy4xMS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlEuEQwj4gADYDxKICpRDAJSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjGUvaG9tZS9zYWluaTUvbWluaWNvbmRhMy9lbnZzL2hmX3JsX2Vudi9saWIvcHl0aG9uMy4xMS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIX2UfZQoaBhoDYwMX19xdWFsbmFtZV9flGgOjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgZjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "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": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.146.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Thu Jan 11 04:09:03 UTC 2024", "Python": "3.11.8", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.2+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
+{"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 0x7fc289e83ba0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc289e83c40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc289e83ce0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc289e83d80>", "_build": "<function ActorCriticPolicy._build at 0x7fc289e83e20>", "forward": "<function ActorCriticPolicy.forward at 0x7fc289e83ec0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc289e83f60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc289e8c040>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc289e8c0e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc289e8c180>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc289e8c220>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc289e8c2c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc289e73940>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713177997655599380, "learning_rate": 0.0003, "tensorboard_log": "logs", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAMYMJz5nPYU+pFGJvexIjL0JEHW6F/mHugAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 0.95, "ent_coef": 0.0, "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:": "gAWV7wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjGUvaG9tZS9zYWluaTUvbWluaWNvbmRhMy9lbnZzL2hmX3JsX2Vudi9saWIvcHl0aG9uMy4xMS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlEuEQwj4gADYDxKICpRDAJSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjGUvaG9tZS9zYWluaTUvbWluaWNvbmRhMy9lbnZzL2hmX3JsX2Vudi9saWIvcHl0aG9uMy4xMS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIX2UfZQoaBhoDYwMX19xdWFsbmFtZV9flGgOjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgZjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.146.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Thu Jan 11 04:09:03 UTC 2024", "Python": "3.11.8", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.2+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7008c697db4db334abbd190392a0595f4580589f96068f48e197332c6a091f2
-size 147692
+oid sha256:53feb9a12dfb1454f5af87378257252ee7bb4082dd05a98a946cfded562002f6
+size 147512

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 0x7f97f7dc3ba0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f97f7dc3c40>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f97f7dc3ce0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f97f7dc3d80>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f97f7dc3e20>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f97f7dc3ec0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f97f7dc3f60>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f97f7dcc040>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f97f7dcc0e0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f97f7dcc180>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f97f7dcc220>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f97f7dcc2c0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fc289e83ba0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc289e83c40>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc289e83ce0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc289e83d80>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fc289e83e20>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fc289e83ec0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc289e83f60>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc289e8c040>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fc289e8c0e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc289e8c180>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc289e8c220>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc289e8c2c0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f97f7dafe00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fc289e73940>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 100352,
-    "_total_timesteps": 100000,
+    "num_timesteps": 1000448,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1713173381150121153,
+    "start_time": 1713177997655599380,
     "learning_rate": 0.0003,
     "tensorboard_log": "logs",
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADDXgT44w6o9FGerPbOksb28HTE9WyBtPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAMYMJz5nPYU+pFGJvexIjL0JEHW6F/mHugAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,32 +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_steps": 1024,
-    "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,
+    "_n_updates": 3908,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -84,7 +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": [],
@@ -92,6 +77,21 @@
         "_np_random": null
     },
     "n_envs": 1,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "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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"

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0747b9525607b8c9373cd7a15d7bfd73d197e745e486ebd1b7db2c0dd4d6f95e
-size 88490
+oid sha256:fa863328f9a3d2d66ba4ef931c47477a3a21fdcbc453c6bddf5ad0954014d33f
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67de68c4dc1c19be894c9e47c648661459673e23a00a1a0dc67d82925f2c91b0
+oid sha256:1eec3ed391910f3ce37512275a0561695bc3fadbab91ceb0753fd7899d618797
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": 21.9663595, "std_reward": 119.42867425885214, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-15T03:01:42.675495"}
+{"mean_reward": 36.246716799999994, "std_reward": 106.753403476096, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-15T04:14:57.915241"}