Upload PPO MountainCar-v0 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: MountainCar-v0
     metrics:
     - type: mean_reward
-      value: -200.00 +/- 0.00
+      value: -105.90 +/- 13.49
       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 0x7840cb9c1c60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7840cb9c1cf0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7840cb9c1d80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7840cb9c1e10>", "_build": "<function ActorCriticPolicy._build at 0x7840cb9c1ea0>", "forward": "<function ActorCriticPolicy.forward at 0x7840cb9c1f30>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7840cb9c1fc0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7840cb9c2050>", "_predict": "<function ActorCriticPolicy._predict at 0x7840cb9c20e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7840cb9c2170>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7840cb9c2200>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7840cb9c2290>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7840cb9be640>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1693356015461351733, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAEAv9L7LRhC8xC0Kv2EZWjtgLgy/V9VVuwyKAL8Bq7y7U9/8vlzUdrvVqeW+PhSbuxvXJb/ofEC7D8ARvw79kTs90he/XHqfOwzb577wRw47EuQlv31GLbzw8xK/Z/aou1GB7L781EO74brVvrkol7yEQQO/njcYPOpxzb4/Qy67lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="}, "_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, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "3", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
+{"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 0x7ff3b61597e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff3b6159870>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff3b6159900>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff3b6159990>", "_build": "<function ActorCriticPolicy._build at 0x7ff3b6159a20>", "forward": "<function ActorCriticPolicy.forward at 0x7ff3b6159ab0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff3b6159b40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff3b6159bd0>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff3b6159c60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff3b6159cf0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff3b6159d80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff3b6159e10>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff3b62fa7c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1605632, "_total_timesteps": 1600000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1693366394531677043, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAET6yj5KWhU86/uJvwbvg70CN6q+6dwuPQ5j7L5tchU7XmqovVUVcT3WHwi/khAWvcYQxz7ZGUg9yGHvvhTsfDylrrq+NiovPBODcr/cqwk9F6fTvsVMv7rh09Y9KBn6PP2Y6r6wKCk9SPRzvrGlqDslY+W+4ekWPGWnLb+dsSO9lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="}, "_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": -0.0035199999999999676, "_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": 1406, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "3", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-MountainCar-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a42809946dce9023fa0645b1020af75d19565468911739ed3e7b5fbbb76d8b28
-size 135470
+oid sha256:f7bb33eae20f3f7157c81c194d172eb1de028df5beeedbd715c2b1286d466d7a
+size 135472

ppo-MountainCar-v0/data

@@ -4,34 +4,34 @@
         ":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 0x7840cb9c1c60>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7840cb9c1cf0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7840cb9c1d80>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7840cb9c1e10>",
-        "_build": "<function ActorCriticPolicy._build at 0x7840cb9c1ea0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7840cb9c1f30>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7840cb9c1fc0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7840cb9c2050>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7840cb9c20e0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7840cb9c2170>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7840cb9c2200>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7840cb9c2290>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7ff3b61597e0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff3b6159870>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff3b6159900>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff3b6159990>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ff3b6159a20>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ff3b6159ab0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff3b6159b40>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff3b6159bd0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ff3b6159c60>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff3b6159cf0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff3b6159d80>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff3b6159e10>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7840cb9be640>"
+        "_abc_impl": "<_abc._abc_data object at 0x7ff3b62fa7c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1015808,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 1605632,
+    "_total_timesteps": 1600000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1693356015461351733,
+    "start_time": 1693366394531677043,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAEAv9L7LRhC8xC0Kv2EZWjtgLgy/V9VVuwyKAL8Bq7y7U9/8vlzUdrvVqeW+PhSbuxvXJb/ofEC7D8ARvw79kTs90he/XHqfOwzb577wRw47EuQlv31GLbzw8xK/Z/aou1GB7L781EO74brVvrkol7yEQQO/njcYPOpxzb4/Qy67lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAET6yj5KWhU86/uJvwbvg70CN6q+6dwuPQ5j7L5tchU7XmqovVUVcT3WHwi/khAWvcYQxz7ZGUg9yGHvvhTsfDylrrq+NiovPBODcr/cqwk9F6fTvsVMv7rh09Y9KBn6PP2Y6r6wKCk9SPRzvrGlqDslY+W+4ekWPGWnLb+dsSO9lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.015808000000000044,
+    "_current_progress_remaining": -0.0035199999999999676,
     "_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'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 248,
+    "_n_updates": 1406,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "gAWVngEAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAgAAAAAAAAABAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksChZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWAgAAAAAAAAABAZRoFEsChZRoGHSUUpSMBl9zaGFwZZRLAoWUjANsb3eUaBAolggAAAAAAAAAmpmZvylcj72UaApLAoWUaBh0lFKUjARoaWdolGgQKJYIAAAAAAAAAJqZGT8pXI89lGgKSwKFlGgYdJRSlIwIbG93X3JlcHKUjA1bLTEuMiAgLTAuMDddlIwJaGlnaF9yZXBylIwLWzAuNiAgMC4wN12UjApfbnBfcmFuZG9tlE51Yi4=",

ppo-MountainCar-v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70d6ba60b2d32d4fa373ea6becd2c2a149794274cbe8b4496f875748909bf06c
+oid sha256:888268708c5dbf50e2481a33cd3b387b218049cd5f5881e56aaf38ce996b7401
 size 81273

ppo-MountainCar-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65b4ef9d69273236fbb1d453089b6f2105b0901f79d12860ab802fdf4a6148db
+oid sha256:720df3404a42dbdb8cd97e8c8289f8bf80e0080c5e486bdc57f9502faab11a42
 size 40001

ppo-MountainCar-v0/system_info.txt

@@ -5,5 +5,5 @@
 - GPU Enabled: True
 - Numpy: 1.23.5
 - Cloudpickle: 2.2.1
-- Gymnasium: 0.29.1
+- Gymnasium: 0.28.1
 - OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-30T00:57:08.333695"}
+{"mean_reward": -105.9, "std_reward": 13.486660075793415, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-30T03:52:03.629931"}