Upload PPO LunarLander-v2 trained agent

README.md

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: ppo
+- name: PPO
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 268.44 +/- 24.51
+      value: 263.43 +/- 26.66
       name: mean_reward
       verified: false
 ---
 
-# **ppo** Agent playing **LunarLander-v2**
-This is a trained model of a **ppo** agent playing **LunarLander-v2**
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
 ## Usage (with Stable-baselines3)

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 0x7ffd6a74f400>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffd6a74f490>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffd6a74f520>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffd6a74f5b0>", "_build": "<function ActorCriticPolicy._build at 0x7ffd6a74f640>", "forward": "<function ActorCriticPolicy.forward at 0x7ffd6a74f6d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ffd6a74f760>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffd6a74f7f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7ffd6a74f880>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffd6a74f910>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffd6a74f9a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffd6a74fa30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ffd6a7476c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689966705052577380, "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": -0.015808000000000044, "_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": 248, "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, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.38-x86_64-with-glibc2.37 # 1-NixOS SMP PREEMPT_DYNAMIC Wed Jul  5 17:27:38 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0", "PyTorch": "2.0.1", "GPU Enabled": "True", "Numpy": "1.24.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.0"}}
+{"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 0x7ffd6a73ab00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffd6a73ab90>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffd6a73ac20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffd6a73acb0>", "_build": "<function ActorCriticPolicy._build at 0x7ffd6a73ad40>", "forward": "<function ActorCriticPolicy.forward at 0x7ffd6a73add0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ffd6a73ae60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffd6a73aef0>", "_predict": "<function ActorCriticPolicy._predict at 0x7ffd6a73af80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffd6a73b010>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffd6a73b0a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffd6a73b130>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ffd6a89dd40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689966705052577380, "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": -0.015808000000000044, "_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": 248, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.38-x86_64-with-glibc2.37 # 1-NixOS SMP PREEMPT_DYNAMIC Wed Jul  5 17:27:38 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0", "PyTorch": "2.0.1", "GPU Enabled": "True", "Numpy": "1.24.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7ca0ab26588241193d089dfc8463f92efae0dcb0bcb9e45a83f118e276e9b72
+oid sha256:d783820a523fc333bd8ae998c50ca69f3496b2c742c8ae6dab5ea56e6674ec13
 size 147124

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 0x7ffd6a74f400>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffd6a74f490>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffd6a74f520>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffd6a74f5b0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7ffd6a74f640>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7ffd6a74f6d0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ffd6a74f760>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffd6a74f7f0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7ffd6a74f880>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffd6a74f910>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffd6a74f9a0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffd6a74fa30>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7ffd6a73ab00>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffd6a73ab90>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffd6a73ac20>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffd6a73acb0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ffd6a73ad40>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ffd6a73add0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ffd6a73ae60>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffd6a73aef0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ffd6a73af80>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffd6a73b010>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffd6a73b0a0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffd6a73b130>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7ffd6a7476c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7ffd6a89dd40>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 268.4428774, "std_reward": 24.514504883748018, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-21T16:15:35.772372"}
+{"mean_reward": 263.42964889202574, "std_reward": 26.657748166296702, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-23T17:33:11.097981"}