Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 3.14 +/- 0.54
+      value: 1409.54 +/- 108.39
       name: mean_reward
       verified: false
 ---

a2c-AntBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd58f992f47196270ffe294ff0f0df7f978075e71c1843b956a19adfba75a8f0
-size 125241
+oid sha256:94f24ecd4a7226513b733cdaa931ce19f49c76a3b99949a94b1c48bf49d6acfb
+size 129248

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 0x7f4f7c25f880>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4f7c25f910>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4f7c25f9a0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4f7c25fa30>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f4f7c25fac0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f4f7c25fb50>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f4f7c25fbe0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4f7c25fc70>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f4f7c25fd00>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4f7c25fd90>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4f7c25fe20>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4f7c25feb0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fc6ea1c83a0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc6ea1c8430>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc6ea1c84c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc6ea1c8550>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fc6ea1c85e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fc6ea1c8670>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc6ea1c8700>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc6ea1c8790>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fc6ea1c8820>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc6ea1c88b0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc6ea1c8940>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc6ea1c89d0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f4f7c265580>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fc6f5e23f00>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -32,12 +32,12 @@
             "weight_decay": 0
         }
     },
-    "num_timesteps": 2016,
-    "_total_timesteps": 2000,
+    "num_timesteps": 3000000,
+    "_total_timesteps": 3000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1682934879604116295,
+    "start_time": 1682941599936045182,
     "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:": "gAWVNQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAQAAAAAAAAEpkz7jwQQ/J0vjPGgrcz+RkMw+mfe/Pv9c3z44cV6+Os+dPt0ilz9ruzs/d4j4v6uX1j71Iok/z7+bvgAd4D4NYSm+S2upP64g9T4IxmY+NNE8v+MqYDw9YXa+GmCPvSerQb+XRCM/uRuwPkIIJT+oOI6+NYq5vFE9Aj9be4k8dGztPJhPBD+0hzU/R8KGPs/wbj5Pyb29zsS2P4Gxiz/tgU+/HMwHP4arib9ckDO+qGUIv6dHdz7ivP0+lNqQPEeAz70cwJq+SO8uv8YJz70/Mqk/l0QjP7kbsD5CCCU/ZGDovlifvj5nRz0+HBigvvNpLb9vMtU+Ap/OPiredT7safs+EYeJP7SLWT9Lsy8+aAGAv0/fGD9nBTK/VYHNvZvc6L6vfyo/3nUBPyEtgL24cVu/Cn90PYy7ZL84O9G8PzKpP5dEIz+5G7A+QgglP18BKT/5YK0+Yw5fPiUY+T6+YZA9rkEtP/OnNT8TZ9i+1yF5PkzvEr8oKq8/VJhdvzGDtD4ZQOQ+npVJvz78lT4W7Ya+4IOcvq76/j5Iowc9IjglvrqdK78Iir8+LSOUvCerQb+XRCM/uRuwPkIIJT+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLHIaUjAFDlHSUUpQu"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -54,22 +54,22 @@
     },
     "_last_original_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_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:": "gAWVggAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQB1t5prULD2MAWyUSxSMAXSUR0AOhM+NcW0rdX2UKGgGR0AaaqzZ6D5CaAdLFWgIR0AOllXiiqQzdX2UKGgGR0AcC8oQWepXaAdLHGgIR0APEoa1kUbldWUu"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 63,
+    "_n_updates": 93750,
     "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:e2dbd26a983429d758969e2484131887a09ab36c87137f8e75fbb450db88643d
+oid sha256:6193371313b5edfcd4d30589f82bb272c06309d4e36259a1b4b9d0b7fa90bac8
 size 56190

a2c-AntBulletEnv-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256d3941020efb257156bceb3287048ab3657b599e58586de2a34474c0069aaf
+oid sha256:455a5bcca1967022cd74e0a54d2effe7b07c63362cfc3801e4fa6c5e82e84f19
 size 56894

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 0x7f4f7c25f880>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4f7c25f910>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4f7c25f9a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4f7c25fa30>", "_build": "<function ActorCriticPolicy._build at 0x7f4f7c25fac0>", "forward": "<function ActorCriticPolicy.forward at 0x7f4f7c25fb50>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f4f7c25fbe0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4f7c25fc70>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4f7c25fd00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4f7c25fd90>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4f7c25fe20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4f7c25feb0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f4f7c265580>"}, "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": 1682934879604116295, "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:": "gAWVggAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQB1t5prULD2MAWyUSxSMAXSUR0AOhM+NcW0rdX2UKGgGR0AaaqzZ6D5CaAdLFWgIR0AOllXiiqQzdX2UKGgGR0AcC8oQWepXaAdLHGgIR0APEoa1kUbldWUu"}, "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 0x7fc6ea1c83a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc6ea1c8430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc6ea1c84c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc6ea1c8550>", "_build": "<function ActorCriticPolicy._build at 0x7fc6ea1c85e0>", "forward": "<function ActorCriticPolicy.forward at 0x7fc6ea1c8670>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc6ea1c8700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc6ea1c8790>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc6ea1c8820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc6ea1c88b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc6ea1c8940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc6ea1c89d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc6f5e23f00>"}, "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": 3000000, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1682941599936045182, "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": 93750, "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"}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf7cd03cd05b5aa66cd80b55858ad07bc7cad89e7ea1baea2c001ff7843c4207
-size 1501919
+oid sha256:5685de9e9c6dcfd1d3761798f9256910ab210ee115b320b3040d71542d2ec90c
+size 1094104

results.json

@@ -1 +1 @@
-{"mean_reward": 3.142435177415609, "std_reward": 0.5381606684335493, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-01T09:54:45.731728"}
+{"mean_reward": 1409.540092239913, "std_reward": 108.38704777441161, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-01T13:15:05.504001"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463119a00d68220564c19fa56d4aa95877bb8c6d8128da9973012f674c066e61
+oid sha256:4c6020692bfcced67eba1987265170f4ce58e5ccfc3b6726f0be6e41e2ea3d11
 size 2176