Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 226.96 +/- 218.35
+      value: 1210.21 +/- 147.67
       name: mean_reward
       verified: false
 ---

a2c-AntBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da8f391fffabaed031a20547a625b174bc89a1b211555341db3c41644e38fecb
-size 125321
+oid sha256:8f2f09428ffd0160f310a11e17617e04341cdf4f0296f3949153504e7714ce42
+size 129246

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 0x7efd2ab431c0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efd2ab43250>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efd2ab432e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efd2ab43370>",
-        "_build": "<function ActorCriticPolicy._build at 0x7efd2ab43400>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7efd2ab43490>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efd2ab43520>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efd2ab435b0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7efd2ab43640>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efd2ab436d0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efd2ab43760>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efd2ab437f0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x78f87b841d80>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78f87b841e10>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78f87b841ea0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78f87b841f30>",
+        "_build": "<function ActorCriticPolicy._build at 0x78f87b841fc0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x78f87b842050>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78f87b8420e0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78f87b842170>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x78f87b842200>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78f87b842290>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78f87b842320>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78f87b8423b0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7efd2ab2fe00>"
+        "_abc_impl": "<_abc._abc_data object at 0x78f87b850a00>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -32,12 +32,12 @@
             "weight_decay": 0
         }
     },
-    "num_timesteps": 2016,
-    "_total_timesteps": 2000,
+    "num_timesteps": 2000000,
+    "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1683299415815006651,
+    "start_time": 1690210156409285231,
     "learning_rate": 0.00096,
     "tensorboard_log": null,
     "lr_schedule": {
@@ -46,7 +46,7 @@
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -54,22 +54,22 @@
     },
     "_last_original_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVNQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAQAAAAAAAAAAAAC0Tpo1AACAPwAAAAAAAAAAAAAAAAAAAAAAAACATz5avQAAAACaLOy/AAAAAD+xDb0AAAAACm/wPwAAAABZdRk9AAAAAO0lAEAAAAAA9xegOwAAAACc6t2/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlj2NQAAgD8AAAAAAAAAAAAAAAAAAAAAAAAAgNBBlT0AAAAAB+HsvwAAAABEz6y8AAAAAMO83z8AAAAAmqObPQAAAAC1zeI/AAAAAPoPzb0AAAAAVUTwvwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJIHcLYAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIBoS5Y9AAAAAIWx4r8AAAAAPTipvQAAAADIzvc/AAAAANX/eb0AAAAA0SjsPwAAAACC0ne9AAAAAFMn7b8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADqdB22AACAPwAAAAAAAAAAAAAAAAAAAAAAAACA5IYNvQAAAABH4/W/AAAAAB686b0AAAAArbXqPwAAAAAPxJG7AAAAAC8LAUAAAAAAjeikPAAAAAAkh+u/AAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLHIaUjAFDlHSUUpQu"
     },
     "_episode_num": 0,
     "use_sde": true,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.008000000000000007,
+    "_current_progress_remaining": 0.0,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVvgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQEYEX2ugYguMAWyUS1iMAXSUR0As/KHwgDA8dX2UKGgGR0ATB0uDjBEbaAdLFWgIR0AtQFZgXuVpdX2UKGgGR0BRlq9kBjnWaAdLmmgIR0At2MHbAUL2dX2UKGgGR0BAWX/YJ3PiaAdLZ2gIR0AvzaFEiMYNdX2UKGgGR0BHZN6ol2NeaAdLXGgIR0AwxO1OTJQtdWUu"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 63,
+    "_n_updates": 62500,
     "n_steps": 8,
     "gamma": 0.99,
     "gae_lambda": 0.9,

a2c-AntBulletEnv-v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7b9f5a16d6f63ab1ebb69f2cb32134644d3efbe78a2eecc0ab7e78a41b6150
+oid sha256:cab70acdcf69aa94474e542b9524030c0544bfa8a3651fedb50a29b18b7c1b51
 size 56190

a2c-AntBulletEnv-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee8178e8d711791879503671592a9490bbb5216291569fcbe1bbb4a38432c693
+oid sha256:519fbf35707c35b59007028e2e0b5235ed9cf8b175a45f548fd866b83985b7f0
 size 56894

a2c-AntBulletEnv-v0/system_info.txt

@@ -1,7 +1,7 @@
-- OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
-- Python: 3.10.11
+- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
+- Python: 3.10.6
 - Stable-Baselines3: 1.8.0
-- PyTorch: 2.0.0+cu118
+- PyTorch: 2.0.1+cu118
 - GPU Enabled: True
 - Numpy: 1.22.4
 - Gym: 0.21.0

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 0x7efd2ab431c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efd2ab43250>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efd2ab432e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efd2ab43370>", "_build": "<function ActorCriticPolicy._build at 0x7efd2ab43400>", "forward": "<function ActorCriticPolicy.forward at 0x7efd2ab43490>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efd2ab43520>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efd2ab435b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7efd2ab43640>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efd2ab436d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efd2ab43760>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efd2ab437f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7efd2ab2fe00>"}, "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": 2016, "_total_timesteps": 2000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1683299415815006651, "learning_rate": 0.00096, "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:": "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": -0.008000000000000007, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVvgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQEYEX2ugYguMAWyUS1iMAXSUR0As/KHwgDA8dX2UKGgGR0ATB0uDjBEbaAdLFWgIR0AtQFZgXuVpdX2UKGgGR0BRlq9kBjnWaAdLmmgIR0At2MHbAUL2dX2UKGgGR0BAWX/YJ3PiaAdLZ2gIR0AvzaFEiMYNdX2UKGgGR0BHZN6ol2NeaAdLXGgIR0AwxO1OTJQtdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 63, "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 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_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]", "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]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_np_random": null}, "n_envs": 4, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.10.11", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 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 0x78f87b841d80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78f87b841e10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78f87b841ea0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78f87b841f30>", "_build": "<function ActorCriticPolicy._build at 0x78f87b841fc0>", "forward": "<function ActorCriticPolicy.forward at 0x78f87b842050>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78f87b8420e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78f87b842170>", "_predict": "<function ActorCriticPolicy._predict at 0x78f87b842200>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78f87b842290>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78f87b842320>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78f87b8423b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78f87b850a00>"}, "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": 1690210156409285231, "learning_rate": 0.00096, "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:": "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 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_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]", "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]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_np_random": null}, "n_envs": 4, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 226.9570232138736, "std_reward": 218.34633518972697, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-05T15:13:32.534876"}
+{"mean_reward": 1210.207041256316, "std_reward": 147.67265313311904, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-24T15:48:20.010782"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218953756a78bd88505f35136c4c8a620137f5827c26c7eccad74ea1e74f5067
+oid sha256:350debf59d8119441e3f4baa7b4e55c24723e4f02dd89e701ed39d33191d780c
 size 2176