retrain

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 255.42 +/- 13.52
+      value: 246.51 +/- 21.34
       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 0x000001D129A4AE60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001D129A4AEF0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001D129A4AF80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001D129A4B010>", "_build": "<function ActorCriticPolicy._build at 0x000001D129A4B0A0>", "forward": "<function ActorCriticPolicy.forward at 0x000001D129A4B130>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001D129A4B1C0>", "_predict": "<function ActorCriticPolicy._predict at 0x000001D129A4B250>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001D129A4B2E0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001D129A4B370>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001D129A4B400>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001D129A4D580>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1666402409659746436, "learning_rate": 0.0, "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": -0.015808000000000044, "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, "system_info": {"OS": "Windows-10-10.0.19044-SP0 10.0.19044", "Python": "3.10.5", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cpu", "GPU Enabled": "False", "Numpy": "1.23.4", "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 0x000001F950F8AE60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001F950F8AEF0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001F950F8AF80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001F950F8B010>", "_build": "<function ActorCriticPolicy._build at 0x000001F950F8B0A0>", "forward": "<function ActorCriticPolicy.forward at 0x000001F950F8B130>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001F950F8B1C0>", "_predict": "<function ActorCriticPolicy._predict at 0x000001F950F8B250>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001F950F8B2E0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001F950F8B370>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001F950F8B400>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001F950F8D640>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1666402409659746436, "learning_rate": 0.0, "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": -0.015808000000000044, "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, "system_info": {"OS": "Windows-10-10.0.19044-SP0 10.0.19044", "Python": "3.10.5", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cpu", "GPU Enabled": "False", "Numpy": "1.23.4", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6130d9e8159ad87533edc55de4f3658638494fdc081961afc93f9b466ed59a
+oid sha256:973d42e31c5ebdc5e9bb3631138f6dfe9ed77ccb030e1b08341564d9cfcb480d
 size 146378

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 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 0x000001D129A4AE60>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001D129A4AEF0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001D129A4AF80>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001D129A4B010>",
-        "_build": "<function ActorCriticPolicy._build at 0x000001D129A4B0A0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x000001D129A4B130>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001D129A4B1C0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x000001D129A4B250>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001D129A4B2E0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001D129A4B370>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001D129A4B400>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x000001F950F8AE60>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001F950F8AEF0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001F950F8AF80>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001F950F8B010>",
+        "_build": "<function ActorCriticPolicy._build at 0x000001F950F8B0A0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000001F950F8B130>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001F950F8B1C0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000001F950F8B250>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001F950F8B2E0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001F950F8B370>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001F950F8B400>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x000001D129A4D580>"
+        "_abc_impl": "<_abc._abc_data object at 0x000001F950F8D640>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 255.42247873071128, "std_reward": 13.521370467262233, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-10-21T22:46:07.579033"}
+{"mean_reward": 246.51098197479413, "std_reward": 21.340796790990264, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-10-21T22:52:22.070376"}