Upload PPO Pendulum-v1 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pendulum-v1
     metrics:
     - type: mean_reward
-      value: -421.52 +/- 342.09
+      value: -150.25 +/- 92.78
       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 0x795124afc0d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795124afc160>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795124afc1f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795124afc280>", "_build": "<function ActorCriticPolicy._build at 0x795124afc310>", "forward": "<function ActorCriticPolicy.forward at 0x795124afc3a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x795124afc430>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795124afc4c0>", "_predict": "<function ActorCriticPolicy._predict at 0x795124afc550>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795124afc5e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795124afc670>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x795124afc700>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x795124aa4f40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 200704, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1723454149510199712, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAABRNcD+oibC+KFR8vpSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="}, "_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": -0.0035199999999999676, "_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": 980, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_shape": [3], "low": "[-1. -1. -8.]", "high": "[1. 1. 8.]", "low_repr": "[-1. -1. -8.]", "high_repr": "[1. 1. 8.]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True]", "bounded_above": "[ True]", "_shape": [1], "low": "[-2.]", "high": "[2.]", "low_repr": "-2.0", "high_repr": "2.0", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "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 0x783cad1f0b80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x783cad1f0c10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x783cad1f0ca0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x783cad1f0d30>", "_build": "<function ActorCriticPolicy._build at 0x783cad1f0dc0>", "forward": "<function ActorCriticPolicy.forward at 0x783cad1f0e50>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x783cad1f0ee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x783cad1f0f70>", "_predict": "<function ActorCriticPolicy._predict at 0x783cad1f1000>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x783cad1f1090>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x783cad1f1120>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x783cad1f11b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x783cad19c5c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 501760, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1723455167935180652, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAN3cfz9OHAa9Y9oKPZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="}, "_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": -0.0035199999999999676, "_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": 2450, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_shape": [3], "low": "[-1. -1. -8.]", "high": "[1. 1. 8.]", "low_repr": "[-1. -1. -8.]", "high_repr": "[1. 1. 8.]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True]", "bounded_above": "[ True]", "_shape": [1], "low": "[-2.]", "high": "[2.]", "low_repr": "-2.0", "high_repr": "2.0", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-Pendulum-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92eaf9c49b764445bcbcbf9991cf46490b0b6ea2265f65344bfeb4c04b21f4fb
-size 138038
+oid sha256:56d2f0339bcc57e5193c7811e39dbda2a7931a162cbafbdd5797f7391c3fdbf6
+size 138039

ppo-Pendulum-v1/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 0x795124afc0d0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795124afc160>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795124afc1f0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795124afc280>",
-        "_build": "<function ActorCriticPolicy._build at 0x795124afc310>",
-        "forward": "<function ActorCriticPolicy.forward at 0x795124afc3a0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x795124afc430>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795124afc4c0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x795124afc550>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795124afc5e0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795124afc670>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x795124afc700>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x783cad1f0b80>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x783cad1f0c10>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x783cad1f0ca0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x783cad1f0d30>",
+        "_build": "<function ActorCriticPolicy._build at 0x783cad1f0dc0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x783cad1f0e50>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x783cad1f0ee0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x783cad1f0f70>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x783cad1f1000>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x783cad1f1090>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x783cad1f1120>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x783cad1f11b0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x795124aa4f40>"
+        "_abc_impl": "<_abc._abc_data object at 0x783cad19c5c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 200704,
-    "_total_timesteps": 200000,
+    "num_timesteps": 501760,
+    "_total_timesteps": 500000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1723454149510199712,
+    "start_time": 1723455167935180652,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAABRNcD+oibC+KFR8vpSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="
+        ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAN3cfz9OHAa9Y9oKPZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,13 +45,13 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwIQWyULUkOaMAWyUS8iMAXSUR0B2jKA+Y+jedX2UKGgGR8CHa5zQu27WaAdLyGgIR0B2kDiOvMbFdX2UKGgGR8CMgA9lEqlQaAdLyGgIR0B2k9flZHNHdX2UKGgGR8CVr9aGpMpPaAdLyGgIR0B2l2x1PnB+dX2UKGgGR8CU+fWUKRdQaAdLyGgIR0B2mytLcsUZdX2UKGgGR8CIQ2HGjsUqaAdLyGgIR0B2nrhGYrrgdX2UKGgGR8CUcb3QUpNLaAdLyGgIR0B2olFH8TBZdX2UKGgGR8CHnmjVx0dSaAdLyGgIR0B2phCF9KEndX2UKGgGR8CDpra9sabXaAdLyGgIR0B2v6Ll3hXKdX2UKGgGR8CIWb4wAU+LaAdLyGgIR0B2w0CwKSgXdX2UKGgGR8CM0XQkX1rZaAdLyGgIR0B2xsF0PpY+dX2UKGgGR8CNGBgrpaA4aAdLyGgIR0B2ylGd7OVxdX2UKGgGR8CEZKEVWS2ZaAdLyGgIR0B2zg+u/1xsdX2UKGgGR8CJDbviLl3haAdLyGgIR0B20a7iADq4dX2UKGgGR8CH69xxT850aAdLyGgIR0B21UBS1maqdX2UKGgGR8B/RPh86V+raAdLyGgIR0B22M0BOpKjdX2UKGgGR8CIBQouwosqaAdLyGgIR0B23GZuyeI3dX2UKGgGR8CIBKwUxmCiaAdLyGgIR0B23+0E5hjOdX2UKGgGR8CNMvSZ0CA+aAdLyGgIR0B2+aLP2PDHdX2UKGgGR8CEV+rcTJyRaAdLyGgIR0B2/Vga3qiXdX2UKGgGR8CIPNDcdo38aAdLyGgIR0B3AOvV3EAHdX2UKGgGR8CNQEwQDmr9aAdLyGgIR0B3BHmr8zhxdX2UKGgGR8CQSvjvd/KAaAdLyGgIR0B3CAd7v5P/dX2UKGgGR8CRCDSDh99daAdLyGgIR0B3C4xcmjTKdX2UKGgGR8CD9lux8lXzaAdLyGgIR0B3Dy9CeEqUdX2UKGgGR8CKnUUmD15CaAdLyGgIR0B3ErI3irDJdX2UKGgGR8CIbPbmEGqxaAdLyGgIR0B3Fi8tf5UMdX2UKGgGR8CCoU1UEPlNaAdLyGgIR0B3GbQa72+PdX2UKGgGR8CAEyIwdsBRaAdLyGgIR0B3OrJ2dNFjdX2UKGgGR8CNg+QlruYyaAdLyGgIR0B3QAPd2xIKdX2UKGgGR8CIZkSZBsyjaAdLyGgIR0B3RQpsoDxLdX2UKGgGR8B5BARL9MsZaAdLyGgIR0B3Sm5LAYYSdX2UKGgGR8CRbEnRLK3eaAdLyGgIR0B3Tmkxh2GJdX2UKGgGR8CNUbHbRF7VaAdLyGgIR0B3UiDdxhlUdX2UKGgGR8CKKbZYgaFVaAdLyGgIR0B3VZRl6JIldX2UKGgGR8CQivwkgOjJaAdLyGgIR0B3WQZ/CqIadX2UKGgGR8CHZyEmplz2aAdLyGgIR0B3XJjoZAIIdX2UKGgGR8CH/0ESM98raAdLyGgIR0B3YBiDujREdX2UKGgGR8CCSSPtlZoxaAdLyGgIR0B3Y9IiC8ODdX2UKGgGR8CIBLs3Q2MsaAdLyGgIR0B3fP/5tWMkdX2UKGgGR8CIPIOyVv/BaAdLyGgIR0B3gIvGp++edX2UKGgGR8CHoxyxRl6JaAdLyGgIR0B3hDt7a7EpdX2UKGgGR8CQi9pz90ihaAdLyGgIR0B3iDbItDlYdX2UKGgGR8CMZyl3Qla9aAdLyGgIR0B3i9j6N2kjdX2UKGgGR8CNTNSLqD9PaAdLyGgIR0B3j3CpFTegdX2UKGgGR8CIOxYV6/qPaAdLyGgIR0B3kzSE12q2dX2UKGgGR8CMXZDtw71aaAdLyGgIR0B3lrGkvboKdX2UKGgGR8CH6JWCEpRXaAdLyGgIR0B3mkjyFwkxdX2UKGgGR8CN0RjwQUYbaAdLyGgIR0B3ndalk6LgdX2UKGgGR8B//BQk5ZKWaAdLyGgIR0B3t0yad+XrdX2UKGgGR8B4dpKRMewLaAdLyGgIR0B3ut1HOKO1dX2UKGgGR8CErumMwUQDaAdLyGgIR0B3vn6UJOWTdX2UKGgGR8CLym9Pk7wKaAdLyGgIR0B3wi8pTdcjdX2UKGgGR8B4kZy8zyjIaAdLyGgIR0B3xeCDmKZVdX2UKGgGR8CNZSXCTEBKaAdLyGgIR0B3yW4RVZLadX2UKGgGR8CNds2ZRbbDaAdLyGgIR0B3zQzvZyuIdX2UKGgGR8CEecUD+zdDaAdLyGgIR0B30KtMfzSUdX2UKGgGR8CNOMHgxagVaAdLyGgIR0B31HIT4+KTdX2UKGgGR8CAOtLteD3/aAdLyGgIR0B32AW56MR6dX2UKGgGR8CDYcPatcOcaAdLyGgIR0B38+9US7GvdX2UKGgGR8CGbmdFvybyaAdLyGgIR0B3+HeXRgJDdX2UKGgGR8CEDECtA9mpaAdLyGgIR0B3/PQQcxTLdX2UKGgGR8CEVVlS0jTsaAdLyGgIR0B4Ab15B1LbdX2UKGgGR8CEA/olD4QCaAdLyGgIR0B4BwPI4lyBdX2UKGgGR8CAQyC2+fyxaAdLyGgIR0B4DBhmXgLrdX2UKGgGR8CEZA91U2k0aAdLyGgIR0B4ESYZ2pyZdX2UKGgGR8CEBLM23rleaAdLyGgIR0B4Fpq8DjiodX2UKGgGR8B4cibBoEjgaAdLyGgIR0B4Go2tMfzSdX2UKGgGR8CAIzS/j81oaAdLyGgIR0B4HghQm/nGdX2UKGgGR8CFH0dNnGsFaAdLyGgIR0B4N0Oz6ab4dX2UKGgGR8CKYuclPacqaAdLyGgIR0B4Os6o2n89dX2UKGgGR8CAGY4DLbHqaAdLyGgIR0B4Pl6KLsKLdX2UKGgGR8B+qoFLWZqmaAdLyGgIR0B4Qf9Nvfj0dX2UKGgGR8CEeDW2gFotaAdLyGgIR0B4RYlAu7HydX2UKGgGR8B4aByU9pyqaAdLyGgIR0B4STZRKpT/dX2UKGgGR8CAGwFcpsoEaAdLyGgIR0B4TMjX4CZGdX2UKGgGR8CQQmESM98raAdLyGgIR0B4UE6aLGaQdX2UKGgGR8CIiHpblijMaAdLyGgIR0B4U89eQdS3dX2UKGgGR8CBRLXoTwlTaAdLyGgIR0B4V2yTpxFRdX2UKGgGR8CEAsh/y5I6aAdLyGgIR0B4WxYHPeHjdX2UKGgGR8CKgugQHzH0aAdLyGgIR0B4dBQP7N0OdX2UKGgGR8CPS1fHggoxaAdLyGgIR0B4d5SzgMtsdX2UKGgGR8B4rQNZvDP4aAdLyGgIR0B4e1ruYx+KdX2UKGgGR8CAC1NKyv9taAdLyGgIR0B4fw1NxlxwdX2UKGgGR8B8iHBbfP5YaAdLyGgIR0B4gqOAAhjfdX2UKGgGR8CAbDZg5R0maAdLyGgIR0B4hiWjXWe6dX2UKGgGR8CERXdUKiPAaAdLyGgIR0B4idL8JlasdX2UKGgGR8CILyUcGTs6aAdLyGgIR0B4jXLt/nW8dX2UKGgGR8CAjo4ZMtbtaAdLyGgIR0B4kQfPomojdX2UKGgGR8CEkwyjYZl4aAdLyGgIR0B4lNWYF7ladX2UKGgGR8CAQmlTm4iHaAdLyGgIR0B4rmLDQ7cPdX2UKGgGR8CEYUqEOAiFaAdLyGgIR0B4sfhqCYkWdX2UKGgGR8CJlAkJrtVraAdLyGgIR0B4tX3yqdYodX2UKGgGR8ByHwUIsyzpaAdLyGgIR0B4udMPBi1BdX2UKGgGR8B4NgaisXBQaAdLyGgIR0B4vsTEit7sdX2UKGgGR8CIlgM2FWXDaAdLyGgIR0B4w2zyBkI5dX2UKGgGR8CAFaO+7Dl6aAdLyGgIR0B4x+NR3u/ldX2UKGgGR8CAGHW+49X+aAdLyGgIR0B4zLjKgZjydX2UKGgGR8B4m5UNrj5saAdLyGgIR0B40cDEFW4mdX2UKGgGR8B4Vxc2R7qqaAdLyGgIR0B41satLcsUdWUu"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 980,
+    "_n_updates": 2450,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",

ppo-Pendulum-v1/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:262c7010c9091544d6e3aed7daafd65d4f792a877609e48ba0c7a8967a0d6e90
+oid sha256:3776b2f105b03cc27939b50c8902c1906d5b9b718acbec273a781910e18edec2
 size 82401

ppo-Pendulum-v1/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ecdec6b1623b7fc0a35a50f727fab64fda51c27c0e50d861ddb7b5b04373a4c
+oid sha256:96233240aabbfd06983fdba16c1609ac42cebb890881714b222a70ade0d36fba
 size 40751

results.json

@@ -1 +1 @@
-{"mean_reward": -421.51727310000007, "std_reward": 342.0916223275373, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-12T09:22:46.954266"}
+{"mean_reward": -150.24566309999997, "std_reward": 92.78171203692794, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-12T09:49:58.458516"}