Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: MountainCar-v0
     metrics:
     - type: mean_reward
-      value: -200.00 +/- 0.00
+      value: -117.00 +/- 3.00
       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 0x17aac0c20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x17aac0cc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x17aac0d60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x17aac0e00>", "_build": "<function ActorCriticPolicy._build at 0x17aac0ea0>", "forward": "<function ActorCriticPolicy.forward at 0x17aac0f40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x17aac0fe0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x17aac1080>", "_predict": "<function ActorCriticPolicy._predict at 0x17aac1120>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x17aac11c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x17aac1260>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x17aac1300>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x17aac60c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True]", "bounded_above": "[ True  True]", "_shape": [2], "low": "[-1.2  -0.07]", "high": "[0.6  0.07]", "low_repr": "[-1.2  -0.07]", "high_repr": "[0.6  0.07]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "3", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 1, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x17a5e5f80>", "reset": "<function RolloutBuffer.reset at 0x17a5e6020>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x17a5e60c0>", "add": "<function RolloutBuffer.add at 0x17a5e6200>", "get": "<function RolloutBuffer.get at 0x17a5e62a0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x17a5e6340>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x17a5ec700>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 8, "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-14.2.1-arm64-arm-64bit Darwin Kernel Version 23.2.0: Wed Nov 15 21:53:18 PST 2023; root:xnu-10002.61.3~2/RELEASE_ARM64_T6000", "Python": "3.11.5", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.2", "GPU Enabled": "False", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}
+{"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 0x28e48b380>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x28e48b420>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x28e48b4c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x28e48b560>", "_build": "<function ActorCriticPolicy._build at 0x28e48b600>", "forward": "<function ActorCriticPolicy.forward at 0x28e48b6a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x28e48b740>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x28e48b7e0>", "_predict": "<function ActorCriticPolicy._predict at 0x28e48b880>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x28e48b920>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x28e48b9c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x28e48ba60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x28e48cd40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 10010624, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1704647138647865000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAPouP7+KvP+8PvONvuuAdT0CPq6+eLWHPIqtSz4K9U89biiIv98etbzVzgq/PGJgPVd3ab89JSe8yaOZvh8SXrp2FN08gmJiPaka/zw6ImU9gUcCvwAAAABx+/2+yrMhOzzCk74LpYU7PcHDPUWhxjz4OMu+t7/GvHSNhr8QCfc8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAABAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0010623999999999079, "_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": 4888, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True]", "bounded_above": "[ True  True]", "_shape": [2], "low": "[-1.2  -0.07]", "high": "[0.6  0.07]", "low_repr": "[-1.2  -0.07]", "high_repr": "[0.6  0.07]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "3", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 16, "n_steps": 1024, "gamma": 1, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x28e1b4360>", "reset": "<function RolloutBuffer.reset at 0x28e1b4400>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x28e1b44a0>", "add": "<function RolloutBuffer.add at 0x28e1b45e0>", "get": "<function RolloutBuffer.get at 0x28e1b4680>", "_get_samples": "<function RolloutBuffer._get_samples at 0x28e1b4720>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x28e1a9d80>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 8, "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-14.2.1-arm64-arm-64bit Darwin Kernel Version 23.2.0: Wed Nov 15 21:53:18 PST 2023; root:xnu-10002.61.3~2/RELEASE_ARM64_T6000", "Python": "3.11.5", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.2", "GPU Enabled": "False", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}

model_ppo_mount_car.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488301c53bd9e74f46e86fad1affc617fc1c313c56af22015f1857150dbb570d
-size 53456
+oid sha256:5ce1a78706e55385e6b6440038d2e79dbcbf1fc98756697a9a97f6195af82d08
+size 138960

model_ppo_mount_car/data

@@ -4,42 +4,54 @@
         ":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 0x17aac0c20>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x17aac0cc0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x17aac0d60>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x17aac0e00>",
-        "_build": "<function ActorCriticPolicy._build at 0x17aac0ea0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x17aac0f40>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x17aac0fe0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x17aac1080>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x17aac1120>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x17aac11c0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x17aac1260>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x17aac1300>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x28e48b380>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x28e48b420>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x28e48b4c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x28e48b560>",
+        "_build": "<function ActorCriticPolicy._build at 0x28e48b600>",
+        "forward": "<function ActorCriticPolicy.forward at 0x28e48b6a0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x28e48b740>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x28e48b7e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x28e48b880>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x28e48b920>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x28e48b9c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x28e48ba60>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x17aac60c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x28e48cd40>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 10010624,
+    "_total_timesteps": 10000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 0.0,
+    "start_time": 1704647138647865000,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": null,
-    "_last_episode_starts": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAPouP7+KvP+8PvONvuuAdT0CPq6+eLWHPIqtSz4K9U89biiIv98etbzVzgq/PGJgPVd3ab89JSe8yaOZvh8SXrp2FN08gmJiPaka/zw6ImU9gUcCvwAAAABx+/2+yrMhOzzCk74LpYU7PcHDPUWhxjz4OMu+t7/GvHSNhr8QCfc8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAABAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 1.0,
+    "_current_progress_remaining": -0.0010623999999999079,
     "_stats_window_size": 100,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 4888,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -57,12 +69,12 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "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",
         "n": "3",
         "start": "0",
         "_shape": [],
         "dtype": "int64",
-        "_np_random": null
+        "_np_random": "Generator(PCG64)"
     },
     "n_envs": 16,
     "n_steps": 1024,
@@ -77,14 +89,14 @@
         "__module__": "stable_baselines3.common.buffers",
         "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
         "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
-        "__init__": "<function RolloutBuffer.__init__ at 0x17a5e5f80>",
-        "reset": "<function RolloutBuffer.reset at 0x17a5e6020>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x17a5e60c0>",
-        "add": "<function RolloutBuffer.add at 0x17a5e6200>",
-        "get": "<function RolloutBuffer.get at 0x17a5e62a0>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x17a5e6340>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x28e1b4360>",
+        "reset": "<function RolloutBuffer.reset at 0x28e1b4400>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x28e1b44a0>",
+        "add": "<function RolloutBuffer.add at 0x28e1b45e0>",
+        "get": "<function RolloutBuffer.get at 0x28e1b4680>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x28e1b4720>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x17a5ec700>"
+        "_abc_impl": "<_abc._abc_data object at 0x28e1a9d80>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,

model_ppo_mount_car/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ccd38deeaf3f0c53b873ecc8333728d6aa62065f9c35da64afd782de4a7450f
-size 1120
+oid sha256:10388ef7a4a792dec1bbc3a3ffd296b020b0422b5d59a2bd7b7e9e45ee14a9b8
+size 81322

model_ppo_mount_car/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a23e3967f6e49f40584d072193e0d929e780fa23056436b43f9a0925ee6af67c
+oid sha256:734e9c0020e684d7380164f381d8f7e9f8f765cce5306f4a3f918e37a0eb8e3a
 size 40306

results.json

@@ -1 +1 @@
-{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-07T17:48:35.077439"}
+{"mean_reward": -117.0, "std_reward": 3.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-07T18:47:16.438790"}