Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 211.61 +/- 21.47
+      value: 204.53 +/- 32.61
       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 0x784771387400>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x784771387490>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x784771387520>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7847713875b0>", "_build": "<function ActorCriticPolicy._build at 0x784771387640>", "forward": "<function ActorCriticPolicy.forward at 0x7847713876d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x784771387760>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7847713877f0>", "_predict": "<function ActorCriticPolicy._predict at 0x784771387880>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x784771387910>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7847713879a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x784771387a30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78477138cc40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1705977627325540063, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_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": -0.015808000000000044, "_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": 156, "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": "[-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 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "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-5.15.133+-x86_64-with-glibc2.31 # 1 SMP Tue Dec 19 13:14:11 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.0+cpu", "GPU Enabled": "False", "Numpy": "1.24.3", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI 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 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 0x7be4e5336cb0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7be4e5336d40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7be4e5336dd0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7be4e5336e60>", "_build": "<function ActorCriticPolicy._build at 0x7be4e5336ef0>", "forward": "<function ActorCriticPolicy.forward at 0x7be4e5336f80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7be4e5337010>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7be4e53370a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7be4e5337130>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7be4e53371c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7be4e5337250>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7be4e53372e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7be4e5343800>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1705977627325540063, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_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": -0.015808000000000044, "_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": 156, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVZgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAADAvwAAwL8AAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAwD8AAMA/AACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFNbLTEuNSAgICAgICAtMS41ICAgICAgIC01LiAgICAgICAgLTUuICAgICAgICAtMy4xNDE1OTI3IC01LgogLTAuICAgICAgICAtMC4gICAgICAgXZSMCWhpZ2hfcmVwcpSMS1sxLjUgICAgICAgMS41ICAgICAgIDUuICAgICAgICA1LiAgICAgICAgMy4xNDE1OTI3IDUuICAgICAgICAxLgogMS4gICAgICAgXZSMCl9ucF9yYW5kb22UTnViLg==", "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 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "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-5.15.133+-x86_64-with-glibc2.31 # 1 SMP Tue Dec 19 13:14:11 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.0+cpu", "GPU Enabled": "False", "Numpy": "1.24.3", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e452d4d1c39dbf538e56ffc9318999cd541afdab478c7c1b4d691e52f3cb81c
+oid sha256:952c3edb87cc1b15db354ce50ca93de1b119d0e0aa8814d72a0169da9a870c8e
 size 145312

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 0x784771387400>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x784771387490>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x784771387520>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7847713875b0>",
-        "_build": "<function ActorCriticPolicy._build at 0x784771387640>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7847713876d0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x784771387760>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7847713877f0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x784771387880>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x784771387910>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7847713879a0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x784771387a30>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7be4e5336cb0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7be4e5336d40>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7be4e5336dd0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7be4e5336e60>",
+        "_build": "<function ActorCriticPolicy._build at 0x7be4e5336ef0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7be4e5336f80>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7be4e5337010>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7be4e53370a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7be4e5337130>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7be4e53371c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7be4e5337250>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7be4e53372e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x78477138cc40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7be4e5343800>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 211.6139608, "std_reward": 21.474579879581302, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-24T05:42:32.973490"}
+{"mean_reward": 204.5280431, "std_reward": 32.60539157649928, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-24T06:16:37.946940"}