Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 258.61 +/- 18.03
+      value: 213.01 +/- 65.75
       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 0x13b2107c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x13b210860>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x13b210900>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x13b2109a0>", "_build": "<function ActorCriticPolicy._build at 0x13b210a40>", "forward": "<function ActorCriticPolicy.forward at 0x13b210ae0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x13b210b80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x13b210c20>", "_predict": "<function ActorCriticPolicy._predict at 0x13b210cc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x13b210d60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x13b210e00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x13b210ea0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x13b20a200>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710643951975450000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM3fWr1cS1e66XCHtdVaJzDb7li6VG+3NAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 0.98, "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": "macOS-14.4-arm64-arm-64bit Darwin Kernel Version 23.4.0: Wed Feb 21 21:44:54 PST 2024; root:xnu-10063.101.15~2/RELEASE_ARM64_T6031", "Python": "3.11.8", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1", "GPU Enabled": "False", "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 0x13b710860>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x13b710900>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x13b7109a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x13b710a40>", "_build": "<function ActorCriticPolicy._build at 0x13b710ae0>", "forward": "<function ActorCriticPolicy.forward at 0x13b710b80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x13b710c20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x13b710cc0>", "_predict": "<function ActorCriticPolicy._predict at 0x13b710d60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x13b710e00>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x13b710ea0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x13b710f40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x13b70a200>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710645272375109000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADNtPbwUtpa6ndYztc0Wk7ALnSa7iH9RNAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 0.98, "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": "macOS-14.4-arm64-arm-64bit Darwin Kernel Version 23.4.0: Wed Feb 21 21:44:54 PST 2024; root:xnu-10063.101.15~2/RELEASE_ARM64_T6031", "Python": "3.11.8", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1", "GPU Enabled": "False", "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 sha256:2d522b0257ff39fdb087d98a894418391f4c4a99eeb26527bfeaa216548d07f3
-size 147074
+oid sha256:2f3a93a9def1cfb03555de3754d69e77adaabbcf21dbdc19c58bcc0eab5399e5
+size 147070

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 0x13b2107c0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x13b210860>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x13b210900>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x13b2109a0>",
-        "_build": "<function ActorCriticPolicy._build at 0x13b210a40>",
-        "forward": "<function ActorCriticPolicy.forward at 0x13b210ae0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x13b210b80>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x13b210c20>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x13b210cc0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x13b210d60>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x13b210e00>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x13b210ea0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x13b710860>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x13b710900>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x13b7109a0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x13b710a40>",
+        "_build": "<function ActorCriticPolicy._build at 0x13b710ae0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x13b710b80>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x13b710c20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x13b710cc0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x13b710d60>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x13b710e00>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x13b710ea0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x13b710f40>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x13b20a200>"
+        "_abc_impl": "<_abc._abc_data object at 0x13b70a200>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,12 +26,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1710643951975450000,
+    "start_time": 1710645272375109000,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM3fWr1cS1e66XCHtdVaJzDb7li6VG+3NAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADNtPbwUtpa6ndYztc0Wk7ALnSa7iH9RNAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,7 +45,7 @@
     "_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'>",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e004271c37c78ab19b5ffc77619cf2d10ae18db5549a0e9d9dda3a69444515b
+oid sha256:d7be518a4c5daec022b205ecf025253e324a119d577b38b0477941ffd81f0caf
 size 87978

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aa76f8b93aad35abd1f879ff56dfe6c70a00cb50300e7873f94c551167ee647
+oid sha256:148b950a4fd3169e1cc00902d9c434f7c4dd23c9e8047deb183de2dda1ca7c49
 size 43634

results.json

@@ -1 +1 @@
-{"mean_reward": 258.613287, "std_reward": 18.033332919188748, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-17T10:55:37.541970"}
+{"mean_reward": 213.00791420000002, "std_reward": 65.75498869238393, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-17T11:17:38.254456"}