Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 325.22 +/- 220.83
+      value: 2095.95 +/- 44.51
       name: mean_reward
       verified: false
 ---

a2c-AntBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37eb2236c322428302dc0338f12ef24a2f6e77ce1051892e05dea7a0f19230fc
-size 67370
+oid sha256:926dc3905b225c5190f6e3e0cac4b9b2f83aeea1e35bba71d8ad2e310089fc25
+size 129265

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 0x7f38f101af70>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f38f1020040>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f38f10200d0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f38f1020160>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f38f10201f0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f38f1020280>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f38f1020310>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f38f10203a0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f38f1020430>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f38f10204c0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f38f1020550>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f38f10205e0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f6829d04c10>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6829d04ca0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6829d04d30>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6829d04dc0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f6829d04e50>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f6829d04ee0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f6829d04f70>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6829d09040>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f6829d090d0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6829d09160>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6829d091f0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6829d09280>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f38f1021240>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f6829d0a280>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -59,28 +59,43 @@
         "_np_random": null
     },
     "n_envs": 4,
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 3000000,
+    "_total_timesteps": 3000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
+    "start_time": 1680100809586030359,
     "learning_rate": 0.00096,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/T3UQTVUdaYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
     },
-    "_last_obs": null,
-    "_last_episode_starts": null,
-    "_last_original_obs": 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:": "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"
+    },
     "_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,
+    "_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": 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 sha256:763e6aa37fb83f8a1ec0724e39a562418a7d4e18293f64bc65670e025bf41c6e
-size 687
+oid sha256:e007a0edc16badf6c47c0094948066faa3ff1c07ce4b9a7480074b3dc6326b6e
+size 56190

a2c-AntBulletEnv-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4071279cfa9bd4331a087e5f7a6661ac2b0086bd48e617a94b27f5ac653d117d
+oid sha256:f227b94b0400856e2b0654b4b01f022466d605ad432ab4d7cb7abe2eb3f0c496
 size 56958

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 0x7f38f101af70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f38f1020040>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f38f10200d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f38f1020160>", "_build": "<function ActorCriticPolicy._build at 0x7f38f10201f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f38f1020280>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f38f1020310>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f38f10203a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f38f1020430>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f38f10204c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f38f1020550>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f38f10205e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f38f1021240>"}, "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": 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-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "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 0x7f6829d04c10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6829d04ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6829d04d30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6829d04dc0>", "_build": "<function ActorCriticPolicy._build at 0x7f6829d04e50>", "forward": "<function ActorCriticPolicy.forward at 0x7f6829d04ee0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f6829d04f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6829d09040>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6829d090d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6829d09160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6829d091f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6829d09280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f6829d0a280>"}, "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": 3000000, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1680100809586030359, "learning_rate": 0.00096, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/T3UQTVUdaYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_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:": "gAWVRAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQJzafonrpq2MAWyUTegDjAF0lEdAs68kI8hcJXV9lChoBkdAoEoqliz9j2gHTegDaAhHQLOvbO32EkB1fZQoaAZHQKBCynPVurJoB03oA2gIR0Czr6PXbuc+dX2UKGgGR0ChX4kGzKLbaAdN6ANoCEdAs7ISJAMUh3V9lChoBkdAn8bSyhSLqGgHTegDaAhHQLO1gEytV7x1fZQoaAZHQJ8xxeZ5Rj1oB03oA2gIR0CztauQMhHLdX2UKGgGR0CbWUoa1kUcaAdN6ANoCEdAs7XM4HX2/XV9lChoBkdAoAfyrWAf+2gHTegDaAhHQLO34ea8Yht1fZQoaAZHQJ+R+UyHmA9oB03oA2gIR0Czu9MLjPv8dX2UKGgGR0CfmTK5TZQIaAdN6ANoCEdAs7wW7HyVfXV9lChoBkdAoBM5iXpnpWgHTegDaAhHQLO8SfjCHh11fZQoaAZHQJ9l65Etuk1oB03oA2gIR0Czv7BH9WIXdX2UKGgGR0CewbdT5wfhaAdN6ANoCEdAs8MjdAPd23V9lChoBkdAoK3jW5H3DmgHTegDaAhHQLPDTvQF9rp1fZQoaAZHQJyRV+G47RxoB03oA2gIR0Czw28Wj45+dX2UKGgGR0CeJizzVc2SaAdN6ANoCEdAs8WJnGsFMnV9lChoBkdAoD3C+vhZQ2gHTegDaAhHQLPI+LkCFK11fZQoaAZHQJ08ZV4oqkNoB03oA2gIR0CzySWfChvjdX2UKGgGR0CgrMw+t8u0aAdN6ANoCEdAs8lILF4s3HV9lChoBkdAoEIdpyp71WgHTegDaAhHQLPMQjpLVWl1fZQoaAZHQJ2ryF9KEnNoB03oA2gIR0Cz0NT7l7tzdX2UKGgGR0CfNo3zcynDaAdN6ANoCEdAs9EA3cYZVHV9lChoBkdAnwKGQXAM2GgHTegDaAhHQLPRIJNj9XN1fZQoaAZHQKAPcDklu3toB03oA2gIR0Cz0zJcs189dX2UKGgGR0CejnRw6ySnaAdN6ANoCEdAs9apMoMKC3V9lChoBkdAnNpQntv4umgHTegDaAhHQLPW1axX4j91fZQoaAZHQJ9UfM4cWCVoB03oA2gIR0Cz1vgTufEodX2UKGgGR0CeuI1XeWOZaAdN6ANoCEdAs9lKRaHKwXV9lChoBkdAnpYfE0iyIGgHTegDaAhHQLPeifr8iwB1fZQoaAZHQJ8BtrylN11oB03oA2gIR0Cz3reUliSadX2UKGgGR0Cfg68CgbqAaAdN6ANoCEdAs97YgOjIrHV9lChoBkdAnhbir1dxAGgHTegDaAhHQLPg9F98Z1p1fZQoaAZHQJ91QGSpzcRoB03oA2gIR0Cz5HeWKMvRdX2UKGgGR0CfQpFm4AjqaAdN6ANoCEdAs+Sr4XXRPXV9lChoBkdAoAwxxWDHwWgHTegDaAhHQLPkzfsu3+d1fZQoaAZHQJyBBwYLsrxoB03oA2gIR0Cz5vBrWRRudX2UKGgGR0CcuQJUHY6GaAdN6ANoCEdAs+vKXu3MIXV9lChoBkdAoBfuucMEzWgHTegDaAhHQLPsFL1VYIV1fZQoaAZHQJ2I/mT1TR9oB03oA2gIR0Cz7Ew+hXbNdX2UKGgGR0CgLwwiJO32aAdN6ANoCEdAs+7trbg0j3V9lChoBkdAoGRIDJU5uWgHTegDaAhHQLPyXftx+8Z1fZQoaAZHQKAjAMBp5/toB03oA2gIR0Cz8out0V8DdX2UKGgGR0CgTJ72tdRjaAdN6ANoCEdAs/KthScbznV9lChoBkdAoLFjo4dZJWgHTegDaAhHQLP0ugNgBtF1fZQoaAZHQJ2NvRplBhRoB03oA2gIR0Cz+IBYigTRdX2UKGgGR0CfRWFMIu5CaAdN6ANoCEdAs/jEqG1x83V9lChoBkdAnSwnSF49o2gHTegDaAhHQLP49HtWuHN1fZQoaAZHQJ5/5dKNAC5oB03oA2gIR0Cz/E4xL0z1dX2UKGgGR0CfZThR64UfaAdN6ANoCEdAs//zFERao3V9lChoBkdAn5X46fapP2gHTegDaAhHQLQAIoTwlSl1fZQoaAZHQKAHmrgflp5oB03oA2gIR0C0AEMQmNR4dX2UKGgGR0CgG6eu/1xsaAdN6ANoCEdAtAJV48lolHV9lChoBkdAnymTByjpLWgHTegDaAhHQLQFwlJHy3F1fZQoaAZHQJ8FphuwX69oB03oA2gIR0C0BfCKm8/VdX2UKGgGR0CfqbA8SwnqaAdN6ANoCEdAtAYQJu2qk3V9lChoBkdAnwhRUR3/xWgHTegDaAhHQLQI2ONHYpV1fZQoaAZHQJ3uMVsUIs1oB03oA2gIR0C0DZmZeAuqdX2UKGgGR0CfVjLEk0JoaAdN6ANoCEdAtA3JWeYlY3V9lChoBkdAlGvf1g6U7mgHTegDaAhHQLQN6zXSSeR1fZQoaAZHQJ+yr420iQloB03oA2gIR0C0D/4NutOmdX2UKGgGR0CfN/xZuAI6aAdN6ANoCEdAtBNxgOSW7nV9lChoBkdAnaEBRqGlAWgHTegDaAhHQLQTnukk8ih1fZQoaAZHQJ58bXPJJXhoB03oA2gIR0C0E7+dTYNBdX2UKGgGR0Cc5pIZZSvUaAdN6ANoCEdAtBXWoAGSp3V9lChoBkdAn1qfRRdhRmgHTegDaAhHQLQbRkOqebx1fZQoaAZHQJ+B9pcophFoB03oA2gIR0C0G3WXTmW/dX2UKGgGR0CfTzb83uNQaAdN6ANoCEdAtBuWHIp6QnV9lChoBkdAnWU+Q+2VmmgHTegDaAhHQLQdsBXCCSR1fZQoaAZHQKAA7flZHNJoB03oA2gIR0C0ISTF+/g0dX2UKGgGR0CgBNtPHktFaAdN6ANoCEdAtCFQiLVFyHV9lChoBkdAnc0jnaFmF2gHTegDaAhHQLQhcQj2SMd1fZQoaAZHQJ+cCoFV1fVoB03oA2gIR0C0I4QzHjp+dX2UKGgGR0CgQHJkPMB7aAdN6ANoCEdAtCfUgFHJ93V9lChoBkdAoUf9ijL0SWgHTegDaAhHQLQoG10T1011fZQoaAZHQJ6l0c94eLhoB03oA2gIR0C0KFIq5LAYdX2UKGgGR0ChjUkovzvraAdN6ANoCEdAtCtn0h/y5XV9lChoBkdAoTPzWTX8O2gHTegDaAhHQLQu5NLDhtN1fZQoaAZHQKFUkmsNlRRoB03oA2gIR0C0LxIOH310dX2UKGgGR0CeX53FDOTraAdN6ANoCEdAtC8xSn+AE3V9lChoBkdAoM6+0w8GLWgHTegDaAhHQLQxOB/qgRN1fZQoaAZHQJsytrwe/6BoB03oA2gIR0C0NMTLwF1TdX2UKGgGR0Cb+7zAvcrRaAdN6ANoCEdAtDULxiG34XV9lChoBkdAnD7UxmCiAWgHTegDaAhHQLQ1QN6gM+h1fZQoaAZHQJuNtt+CsfdoB03oA2gIR0C0OIjqOcUedX2UKGgGR0Ceb9FBIFvAaAdN6ANoCEdAtDyaicoYvXV9lChoBkdAncSPexfOU2gHTegDaAhHQLQ8yBXjlxR1fZQoaAZHQJ7LUh+vyLBoB03oA2gIR0C0POm/336AdX2UKGgGR0CdqPmaYu01aAdN6ANoCEdAtD8GXD3ueHV9lChoBkdAm/OVqWTouGgHTegDaAhHQLRChSi/O+t1fZQoaAZHQJY5wixFAmloB03oA2gIR0C0QrJ2pyZKdX2UKGgGR0Ce+bnDBMzuaAdN6ANoCEdAtELTMUypJnV9lChoBkdAnwwSKekHlmgHTegDaAhHQLRFbFPSDyx1fZQoaAZHQKEm6aAnUlRoB03oA2gIR0C0SlawIMScdX2UKGgGR0CgTCl1B+nZaAdN6ANoCEdAtEqGRgZ0jnV9lChoBkdAoWmsTJyQxWgHTegDaAhHQLRKqJ17pmp1fZQoaAZHQKDp9hESdvtoB03oA2gIR0C0TLg3Lmp3dX2UKGgGR0Chu/oiLVFyaAdN6ANoCEdAtFAkD4gzQHV9lChoBkdAobkDQAuIymgHTegDaAhHQLRQT7GvOhV1fZQoaAZHQKDzC6kqMFVoB03oA2gIR0C0UHANCqp+dX2UKGgGR0CgTCmnfl6raAdN6ANoCEdAtFKGsySFG3VlLg=="}, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "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 sha256:27ff81216d78b179c57322c53f48601ede973d76458796fcdf242b0aee06cc20
-size 374126
+oid sha256:b0a778af4961e91671b457f6add679a15df9ac69f524dd066c3e8ec2a32786b9
+size 1327360

results.json

@@ -1 +1 @@
-{"mean_reward": 325.22054684609174, "std_reward": 220.82899618321915, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-29T12:06:52.089688"}
+{"mean_reward": 2095.9535594632093, "std_reward": 44.507638426776836, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-29T16:16:37.758309"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d96ba06e37511ea33a42feda7687377863601780b8c5072ac08e8cdd7b6e500
-size 2123
+oid sha256:9d929d7800eac3f965ec052ce001fd0939d40c0a8d9bea12a85d905f4db04063
+size 2136