Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 306.93 +/- 11.88
+      value: 308.35 +/- 9.96
       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 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 0x7efc82e2fbe0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efc82e2fc70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efc82e2fd00>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efc82e2fd90>", "_build": "<function ActorCriticPolicy._build at 0x7efc82e2fe20>", "forward": "<function ActorCriticPolicy.forward at 0x7efc82e2feb0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efc82e2ff40>", "_predict": "<function ActorCriticPolicy._predict at 0x7efc82e40040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efc82e400d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efc82e40160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efc82e401f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7efc82e3c740>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVPAEAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc3RhcnSUSwCMBl9zaGFwZZQpjAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UjBRudW1weS5yYW5kb20uX3BpY2tsZZSMEF9fZ2VuZXJhdG9yX2N0b3KUk5SMBVBDRzY0lIWUUpR9lCiMDWJpdF9nZW5lcmF0b3KUjAVQQ0c2NJSMBXN0YXRllH2UKGgbihGVqSmXwP0gua/xXorFE4KIAIwDaW5jlIoRnYMK7BzkRiGiMnnJyGforgB1jApoYXNfdWludDMylEsAjAh1aW50ZWdlcpRLAHVidWIu", "n": 4, "start": 0, "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 16, "num_timesteps": 33564256, "_total_timesteps": 80000000, "_num_timesteps_at_start": 0, "seed": 3779038994, "action_noise": null, "start_time": 1670977661545725413, "learning_rate": 0.0003, "tensorboard_log": "tensorboard-logs/ppo-LunarLander-v2-80m/LunarLander-v2", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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": 0.5805696, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 8192, "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:": "gAWV8QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMXy9ob21lL21hcmt1cy9zcmMvYWkvaGYtZHJsLy52ZW52L2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgUMCBAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxfL2hvbWUvbWFya3VzL3NyYy9haS9oZi1kcmwvLnZlbnYvbGliL3B5dGhvbjMuMTAvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.15.0-56-generic-x86_64-with-glibc2.35 #62-Ubuntu SMP Tue Nov 22 19:54:14 UTC 2022", "Python": "3.10.6", "Stable-Baselines3": "2.0.0a0", "PyTorch": "1.13.0+cu117", "GPU Enabled": "False", "Numpy": "1.23.5", "Gym": "0.26.2"}}
+{"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 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 0x7f9ce7923be0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9ce7923c70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9ce7923d00>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9ce7923d90>", "_build": "<function ActorCriticPolicy._build at 0x7f9ce7923e20>", "forward": "<function ActorCriticPolicy.forward at 0x7f9ce7923eb0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9ce7923f40>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9ce7934040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9ce79340d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9ce7934160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9ce79341f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f9ce7930ec0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVPAEAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc3RhcnSUSwCMBl9zaGFwZZQpjAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UjBRudW1weS5yYW5kb20uX3BpY2tsZZSMEF9fZ2VuZXJhdG9yX2N0b3KUk5SMBVBDRzY0lIWUUpR9lCiMDWJpdF9nZW5lcmF0b3KUjAVQQ0c2NJSMBXN0YXRllH2UKGgbihGVqSmXwP0gua/xXorFE4KIAIwDaW5jlIoRnYMK7BzkRiGiMnnJyGforgB1jApoYXNfdWludDMylEsAjAh1aW50ZWdlcpRLAHVidWIu", "n": 4, "start": 0, "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 16, "num_timesteps": 33564256, "_total_timesteps": 80000000, "_num_timesteps_at_start": 0, "seed": 3779038994, "action_noise": null, "start_time": 1670977661545725413, "learning_rate": 0.0003, "tensorboard_log": "tensorboard-logs/ppo-LunarLander-v2-80m/LunarLander-v2", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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": 0.5805696, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 8192, "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, "system_info": {"OS": "Linux-5.15.0-56-generic-x86_64-with-glibc2.35 #62-Ubuntu SMP Tue Nov 22 19:54:14 UTC 2022", "Python": "3.10.6", "Stable-Baselines3": "2.0.0a0", "PyTorch": "1.13.0+cu117", "GPU Enabled": "False", "Numpy": "1.23.5", "Gym": "0.26.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec5d90ad40699106fa774f6742f3a018292b1dc9726df0cc71850399cfd787c3
+oid sha256:80621ac6ebeedf989ac2743e7e93d608bcb24f052e7c8ba35ca814305b3d9aae
 size 147391

ppo-LunarLander-v2/data

@@ -4,19 +4,19 @@
         ":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 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 0x7efc82e2fbe0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efc82e2fc70>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efc82e2fd00>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efc82e2fd90>",
-        "_build": "<function ActorCriticPolicy._build at 0x7efc82e2fe20>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7efc82e2feb0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efc82e2ff40>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7efc82e40040>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efc82e400d0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efc82e40160>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efc82e401f0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f9ce7923be0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9ce7923c70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9ce7923d00>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9ce7923d90>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f9ce7923e20>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f9ce7923eb0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9ce7923f40>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f9ce7934040>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9ce79340d0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9ce7934160>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9ce79341f0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7efc82e3c740>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f9ce7930ec0>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 306.9291374984359, "std_reward": 11.877906243255918, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-14T09:55:49.576922"}
+{"mean_reward": 308.35437255676595, "std_reward": 9.964034614207234, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-14T10:04:02.994486"}