Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 1500.16 +/- 82.38
+      value: 1394.91 +/- 118.72
       name: mean_reward
       verified: false
 ---

a2c-AntBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:343eaa52df30c1dba7fef618469589ed07a57949a85b60adfda7899a24b50c92
+oid sha256:3ac317b1e4a83770ae70d58a9e40b82a91ea7f28ff29f43a699d86ab7e791c08
 size 129620

a2c-AntBulletEnv-v0/data

@@ -4,20 +4,20 @@
         ":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 0x7f51f7b713a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f51f7b71430>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f51f7b714c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f51f7b71550>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f51f7b715e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f51f7b71670>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f51f7b71700>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f51f7b71790>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f51f7b71820>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f51f7b718b0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f51f7b71940>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f51f7b719d0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f5164972310>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f51649723a0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5164972430>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f51649724c0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f5164972550>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f51649725e0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5164972670>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5164972700>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f5164972790>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5164972820>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f51649728b0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5164972940>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f51f7b6cd00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f5164974740>"
     },
     "verbose": 1,
     "policy_kwargs": {

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 0x7f51f7b713a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f51f7b71430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f51f7b714c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f51f7b71550>", "_build": "<function ActorCriticPolicy._build at 0x7f51f7b715e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f51f7b71670>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f51f7b71700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f51f7b71790>", "_predict": "<function ActorCriticPolicy._predict at 0x7f51f7b71820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f51f7b718b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f51f7b71940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f51f7b719d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f51f7b6cd00>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 2000000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688359629582614059, "learning_rate": 0.00096, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVNQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAQAAAAAAAMVidD5UY34/B3iNvGd2lD9GtJY/n4c6ve2S3D7EjlK+PZRlPXOIPb/VUWS/z8MxP2xVCb786GM+fEm9vraXZj5ZQ5Y/9MuGvgi5qz0xFsQ+eUctv2JSHz56jw0+KJlrv5EygL9mNSU/6jTvvxjCgz9u5PE+30Qhv54+8z6eTJk+VAGkvuHV1z7PHkq8q/uyv3laKT9O62I+RINQPyL4lL8kjWC/X8E9P78JLL4bXV08hxISvp1oRz/0LCw/5VQRvw4Icb4R8YU/qkY5vGjccj+RMoC/ZjUlP3L8CD+ysni/yt7iPod8Hj9lAZw+CTFDP0I/iD/Cdj0/jtBXvq96Y78xaKI+oo7MP8VwUT8vUa0+JCiUv7Z7xT3hC+U++jG+v8a5Pj+ZMuq+CTG+vow5aD9yesO+GNigvoYFoz00wYi/BZt/P9tXxr9y/Ag/srJ4v1zuYL7g6Hm/5iSWPr2eb77sw9c/PqUxP2+zBj8hWx+/zg3+vcxuDj8mwGq/4E5wvNTsLD6R7XI/QxMTPpCHzj5/ixI/dGp6PyaNNT863Ua9J5bxPwyk7j1aFFQ/f7N5PpEygL9mNSU/cvwIPxjCgz+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLHIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_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": 62500, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "_shape": [28], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.19.0-46-generic-x86_64-with-glibc2.35 # 47~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jun 21 15:35:31 UTC 2", "Python": "3.9.16", "Stable-Baselines3": "2.0.0", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.25.0", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.23.0"}}
+{"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 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 0x7f5164972310>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f51649723a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5164972430>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f51649724c0>", "_build": "<function ActorCriticPolicy._build at 0x7f5164972550>", "forward": "<function ActorCriticPolicy.forward at 0x7f51649725e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5164972670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5164972700>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5164972790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5164972820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f51649728b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5164972940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5164974740>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 2000000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688359629582614059, "learning_rate": 0.00096, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVNQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAQAAAAAAAAAAAAAXvus1AACAPwAAAAAAAAAAAAAAAAAAAAAAAACADvWzvAAAAADFe/6/AAAAAJohmToAAAAACx7tPwAAAACCJzY9AAAAALoN6z8AAAAA0IoEvAAAAACgxPu/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJgatgAAgD8AAAAAAAAAAAAAAAAAAAAAAAAAgMh4jr0AAAAA5qXivwAAAADsmP+9AAAAAK7C4z8AAAAAwLK2uwAAAAALyNs/AAAAANjdMz0AAAAAwgb3vwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAN8h3zUAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIARsnQ9AAAAAKs14L8AAAAAEJkNPgAAAADGiwBAAAAAAKqt6j0AAAAA+cnaPwAAAADcT/Y9AAAAAOAK578AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADuNwKzAACAPwAAAAAAAAAAAAAAAAAAAAAAAACAeH6aPQAAAABP9fq/AAAAAMN8qj0AAAAAfo4AQAAAAAAjsoU8AAAAAHev7T8AAAAAFm8CPQAAAACKxvC/AAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLHIaUjAFDlHSUUpQu"}, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_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": 62500, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "_shape": [28], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.19.0-46-generic-x86_64-with-glibc2.35 # 47~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jun 21 15:35:31 UTC 2", "Python": "3.9.16", "Stable-Baselines3": "2.0.0", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.25.0", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.23.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 1500.157654607389, "std_reward": 82.38134416511369, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-02T22:15:08.420260"}
+{"mean_reward": 1394.9078968830581, "std_reward": 118.72162598453404, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-02T22:32:20.260447"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc7729ddd2c96f0f4580e5c776e471b5e96503e4f566c09dfaf5111ad6f8df3f
+oid sha256:f795c845755bbaa6236287f4afb690adbe4e6b7dfd8a61072a6973ea76eabc6f
 size 2335