Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 279.21 +/- 11.68
+      value: 296.40 +/- 19.52
       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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 0x2901ceb90>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x2901cec20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x2901cecb0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x2901ced40>", "_build": "<function ActorCriticPolicy._build at 0x2901cedd0>", "forward": "<function ActorCriticPolicy.forward at 0x2901cee60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x2901ceef0>", "_predict": "<function ActorCriticPolicy._predict at 0x2901cef80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x2901cf010>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x2901cf0a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x2901cf130>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x2901c6100>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 10010624, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1679539101.9133031, "learning_rate": 0.0003, "tensorboard_log": null, "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": -0.0010623999999999079, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2444, "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": "macOS-13.2.1-arm64-arm-64bit Darwin Kernel Version 22.3.0: Mon Jan 30 20:38:37 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T6000", "Python": "3.10.9", "Stable-Baselines3": "1.5.0", "PyTorch": "1.13.1", "GPU Enabled": "False", "Numpy": "1.22.4", "Gym": "0.21.0"}}
+{"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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 0x17e37fac0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x17e37fb50>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x17e37fbe0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x17e37fc70>", "_build": "<function ActorCriticPolicy._build at 0x17e37fd00>", "forward": "<function ActorCriticPolicy.forward at 0x17e37fd90>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x17e37fe20>", "_predict": "<function ActorCriticPolicy._predict at 0x17e37feb0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x17e37ff40>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x17e384040>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x17e3840d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x17e37a780>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 10010624, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1679539101.9133031, "learning_rate": 0.0003, "tensorboard_log": null, "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": -0.0010623999999999079, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2444, "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": "macOS-13.2.1-arm64-arm-64bit Darwin Kernel Version 22.3.0: Mon Jan 30 20:38:37 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T6000", "Python": "3.10.9", "Stable-Baselines3": "1.5.0", "PyTorch": "1.13.1", "GPU Enabled": "False", "Numpy": "1.22.4", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb939ad9dc2607f2fdfddbf494f7c1859c6ae5429febc0ec0234ae456269c92
-size 146417
+oid sha256:e7ec1746c01e9488ce6fb9563a1ec984f0a6225ed8edb284ef6a74e7c51d97a1
+size 146433

ppo-LunarLander-v2/data

@@ -4,25 +4,25 @@
         ":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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 0x2901ceb90>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x2901cec20>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x2901cecb0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x2901ced40>",
-        "_build": "<function ActorCriticPolicy._build at 0x2901cedd0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x2901cee60>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x2901ceef0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x2901cef80>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x2901cf010>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x2901cf0a0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x2901cf130>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x17e37fac0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x17e37fb50>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x17e37fbe0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x17e37fc70>",
+        "_build": "<function ActorCriticPolicy._build at 0x17e37fd00>",
+        "forward": "<function ActorCriticPolicy.forward at 0x17e37fd90>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x17e37fe20>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x17e37feb0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x17e37ff40>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x17e384040>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x17e3840d0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x2901c6100>"
+        "_abc_impl": "<_abc._abc_data object at 0x17e37a780>"
     },
     "verbose": 1,
     "policy_kwargs": {},
     "observation_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             8
@@ -35,7 +35,7 @@
     },
     "action_space": {
         ":type:": "<class 'gym.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
         "n": 4,
         "_shape": [],
         "dtype": "int64",

results.json

@@ -1 +1 @@
-{"mean_reward": 279.21314713334147, "std_reward": 11.67965226754592, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-22T23:27:38.411707"}
+{"mean_reward": 296.4032037561065, "std_reward": 19.515129569676912, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-23T08:37:08.976020"}