Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 289.97 +/- 12.59
+      value: 285.27 +/- 22.82
       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 0x0000019B03284360>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000019B03284400>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000019B032844A0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000019B03284540>", "_build": "<function ActorCriticPolicy._build at 0x0000019B032845E0>", "forward": "<function ActorCriticPolicy.forward at 0x0000019B03284680>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000019B03284720>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000019B032847C0>", "_predict": "<function ActorCriticPolicy._predict at 0x0000019B03284860>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000019B03284900>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000019B032849A0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000019B03284A40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000019B03280800>"}, "verbose": 5, "policy_kwargs": {}, "num_timesteps": 1007616, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1697617094053527800, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVNQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAAAAAAAAAICzBL0unJe8spHxPbaklzxTWP+94c2LPQAAgD8AAIA/AAvmPPjjDT/INio908LUvtubBD3aKyA7AAAAAAAAAADzhpW9PH1xPaXL9j1jH7G+pZjIvILuiz0AAAAAAAAAALOciD1Iw4e6urBSuXqaQ7Rbnbq6aF91OAAAgD8AAIA/ZleHPPY8Y7qVs4qz0KyUL2PoKTmyNs0zAACAPwAAgD/mMMS9iEbRPTt2kD6sMse+MzMQPg3W/TwAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBksIhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYGAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLBoWUjAFDlHSUUpQu"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "_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": 820, "n_steps": 2048, "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, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "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:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 6, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.11.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.1", "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 0x000001FD9B740360>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001FD9B740400>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001FD9B7404A0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001FD9B740540>", "_build": "<function ActorCriticPolicy._build at 0x000001FD9B7405E0>", "forward": "<function ActorCriticPolicy.forward at 0x000001FD9B740680>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001FD9B740720>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001FD9B7407C0>", "_predict": "<function ActorCriticPolicy._predict at 0x000001FD9B740860>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001FD9B740900>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001FD9B7409A0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001FD9B740A40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001FD9B744380>"}, "verbose": 5, "policy_kwargs": {}, "num_timesteps": 1007616, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1697617094053527800, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVNQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAAAAAAAAAICzBL0unJe8spHxPbaklzxTWP+94c2LPQAAgD8AAIA/AAvmPPjjDT/INio908LUvtubBD3aKyA7AAAAAAAAAADzhpW9PH1xPaXL9j1jH7G+pZjIvILuiz0AAAAAAAAAALOciD1Iw4e6urBSuXqaQ7Rbnbq6aF91OAAAgD8AAIA/ZleHPPY8Y7qVs4qz0KyUL2PoKTmyNs0zAACAPwAAgD/mMMS9iEbRPTt2kD6sMse+MzMQPg3W/TwAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBksIhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYGAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLBoWUjAFDlHSUUpQu"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "_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": 820, "n_steps": 2048, "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, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "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:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 6, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.11.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.1", "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 sha256:7a1788eea1a5ffe5e88576c8590113468e3a7e812a267b588d3256eff6a1b395
+oid sha256:d584c4bdb3cdc085539bfe5d8759f009463d8eae17627f10328969ffd2d23931
 size 147940

ppo-LunarLander-v2/data

@@ -4,20 +4,20 @@
         ":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 0x0000019B03284360>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000019B03284400>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000019B032844A0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000019B03284540>",
-        "_build": "<function ActorCriticPolicy._build at 0x0000019B032845E0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x0000019B03284680>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000019B03284720>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000019B032847C0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x0000019B03284860>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000019B03284900>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000019B032849A0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000019B03284A40>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x000001FD9B740360>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001FD9B740400>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001FD9B7404A0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001FD9B740540>",
+        "_build": "<function ActorCriticPolicy._build at 0x000001FD9B7405E0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000001FD9B740680>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001FD9B740720>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001FD9B7407C0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000001FD9B740860>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001FD9B740900>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001FD9B7409A0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001FD9B740A40>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x0000019B03280800>"
+        "_abc_impl": "<_abc._abc_data object at 0x000001FD9B744380>"
     },
     "verbose": 5,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 289.96977519999996, "std_reward": 12.589641508905972, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-18T12:34:58.541100"}
+{"mean_reward": 285.26843240000005, "std_reward": 22.818296820480217, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-18T12:35:43.261509"}