Initial commit

Browse files

Files changed (8) hide show

README.md +1 -1
a2c-AntBulletEnv-v0.zip +2 -2
a2c-AntBulletEnv-v0/data +33 -44
a2c-AntBulletEnv-v0/policy.optimizer.pth +2 -2
a2c-AntBulletEnv-v0/policy.pth +1 -1
config.json +1 -1
results.json +1 -1
vec_normalize.pkl +2 -2

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ model-index:
       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 1721.35 +/- 32.60
       name: mean_reward
       verified: false
 ---

       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
+      value: 8.40 +/- 0.29
       name: mean_reward
       verified: false
 ---

a2c-AntBulletEnv-v0.zip CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbff4317621d09002e148142d76c8b6d7eec90e44d7ce6d42010f88eb87494e3
-size 129260

 version https://git-lfs.github.com/spec/v1
+oid sha256:1a1ae24f79dae123f3d4b654dd4631a0a4a5b063c82064310bb8c0484d45c419
+size 67573

a2c-AntBulletEnv-v0/data CHANGED Viewed

@@ -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 0x7f42389b3af0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f42389b3b80>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f42389b3c10>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f42389b3ca0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f42389b3d30>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f42389b3dc0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f42389b3e50>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f42389b3ee0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f42389b3f70>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f42389b7040>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f42389b70d0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f42389b7160>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f42389b05d0>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -34,68 +34,57 @@
     },
     "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,
-    "num_timesteps": 2000000,
-    "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1677355377325739242,
     "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:": "gAWVNQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAQAAAAAAAAAAAABCZ2I2AACAPwAAAAAAAAAAAAAAAAAAAAAAAACAMc4ovQAAAADw7+q/AAAAAOkNnj0AAAAA07bqPwAAAABfKNA8AAAAAMcl/z8AAAAAk0snuQAAAADUrOu/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA2fs8tgAAgD8AAAAAAAAAAAAAAAAAAAAAAAAAgNinWzwAAAAAnWHgvwAAAAAYJr29AAAAALag8j8AAAAADvmcPQAAAAB+fPg/AAAAAC+8tz0AAAAAXOTfvwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAI3rmDYAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIC8gA+9AAAAACwk+L8AAAAAa/KtPQAAAAC4ets/AAAAAErYyz0AAAAAF5HdPwAAAABCcbA8AAAAAMQ6AcAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQ6JW1AACAPwAAAAAAAAAAAAAAAAAAAAAAAACASWv2vAAAAACNcN6/AAAAAFwn3L0AAAAAEy/7PwAAAAApC8g9AAAAAL/D9T8AAAAAGpOLPQAAAAAqRd2/AAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLHIaUjAFDlHSUUpQu"
-    },
     "_episode_num": 0,
     "use_sde": true,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 0.0,
-    "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,

         ":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 0x7f223d3f03a0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f223d3f0430>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f223d3f04c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f223d3f0550>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f223d3f05e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f223d3f0670>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f223d3f0700>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f223d3f0790>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f223d3f0820>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f223d3f08b0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f223d3f0940>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f223d3f09d0>",
         "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f223d3e4cc0>"
     },
     "verbose": 1,
     "policy_kwargs": {
     },
     "observation_space": {
         ":type:": "<class 'gym.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 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVwwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAACAvwAAgL8AAIC/AACAvwAAgL8AAIC/AACAvwAAgL+UaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAgD8AAIA/AACAPwAAgD8AAIA/AACAPwAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjAQtMS4wlIwJaGlnaF9yZXBylIwDMS4wlIwKX25wX3JhbmRvbZROdWIu",
         "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,
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
+    "start_time": null,
     "learning_rate": 0.00096,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"
     },
+    "_last_obs": null,
+    "_last_episode_starts": null,
+    "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": true,
     "sde_sample_freq": -1,
+    "_current_progress_remaining": 1,
+    "ep_info_buffer": null,
+    "ep_success_buffer": null,
+    "_n_updates": 0,
     "n_steps": 8,
     "gamma": 0.99,
     "gae_lambda": 0.9,

a2c-AntBulletEnv-v0/policy.optimizer.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd98c806ea6dc6e0c898e1127b00801a6e3545784965b6e10620efb47327e36
-size 56190

 version https://git-lfs.github.com/spec/v1
+oid sha256:763e6aa37fb83f8a1ec0724e39a562418a7d4e18293f64bc65670e025bf41c6e
+size 687

a2c-AntBulletEnv-v0/policy.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55059c3f05d6f83aa11c5b14dd8b1e5dc60547f90ff74ae4940ae7b3b1b103fb
 size 56958

 version https://git-lfs.github.com/spec/v1
+oid sha256:e0b8f94cde905f0b357471adbaf102a8020e6442beb24b0d8d2dac2b9f89d826
 size 56958

config.json CHANGED Viewed

@@ -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 0x7f42389b3af0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f42389b3b80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f42389b3c10>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f42389b3ca0>", "_build": "<function ActorCriticPolicy._build at 0x7f42389b3d30>", "forward": "<function ActorCriticPolicy.forward at 0x7f42389b3dc0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f42389b3e50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f42389b3ee0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f42389b3f70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f42389b7040>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f42389b70d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f42389b7160>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f42389b05d0>"}, "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}}, "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, "num_timesteps": 2000000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677355377325739242, "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, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "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 0x7f223d3f03a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f223d3f0430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f223d3f04c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f223d3f0550>", "_build": "<function ActorCriticPolicy._build at 0x7f223d3f05e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f223d3f0670>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f223d3f0700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f223d3f0790>", "_predict": "<function ActorCriticPolicy._predict at 0x7f223d3f0820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f223d3f08b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f223d3f0940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f223d3f09d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f223d3e4cc0>"}, "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}}, "observation_space": {":type:": "<class 'gym.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 'gym.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, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.00096, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": 1, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}

results.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"mean_reward": ~~1721~~.~~3521707716397~~, "std_reward": 32.~~60062599862085~~, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-~~25T21~~:43:33.~~260099~~"}


1	+ {"mean_reward": 8.4005405575037, "std_reward": 0.2948030349009093, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T11:40:27.783809"}

vec_normalize.pkl CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976023224ca5435c357b19f0bd33cde94c3fd5e2358840711a5b7a413240d81b
-size 2136

 version https://git-lfs.github.com/spec/v1
+oid sha256:a492a76290837046d4e83920e944f6d78824bdfefab154ede6140f076f7abb65
+size 2123