Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 9.99 +/- 0.00
+      value: 2314.73 +/- 78.83
       name: mean_reward
       verified: false
 ---

a2c-AntBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e279f3aa6cc8203422c46527b7ed61682b676b456b02bc5de85829173f001d
-size 65252
+oid sha256:7512bfa5e6539785320267661c46002bc680be721a6e6aa10eef2e1d592a70cc
+size 125180

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 0x7fea30d76b90>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fea30d76c20>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fea30d76cb0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fea30d76d40>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fea30d76dd0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fea30d76e60>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fea30d76ef0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fea30d76f80>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fea30d77010>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fea30d770a0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fea30d77130>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fea30d771c0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fec5eb0ef80>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fec5eb0f010>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fec5eb0f0a0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fec5eb0f130>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fec5eb0f1c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fec5eb0f250>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fec5eb0f2e0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fec5eb0f370>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fec5eb0f400>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fec5eb0f490>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fec5eb0f520>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fec5eb0f5b0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fea30d80140>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fec5eb0aa00>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -30,32 +30,54 @@
             "weight_decay": 0
         }
     },
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 2500000,
+    "_total_timesteps": 2500000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
-    "learning_rate": 0.0008,
+    "start_time": 1686498469881797132,
+    "learning_rate": 0.0005,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":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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"
     },
-    "_last_obs": null,
-    "_last_episode_starts": null,
-    "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 1,
+    "_current_progress_remaining": 0.0,
     "_stats_window_size": 100,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 125000,
+    "n_steps": 5,
+    "gamma": 0.99,
+    "gae_lambda": 1.0,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "normalize_advantage": false,
     "observation_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             28
@@ -68,7 +90,7 @@
     },
     "action_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             8
@@ -79,12 +101,5 @@
         "bounded_above": "[ True  True  True  True  True  True  True  True]",
         "_np_random": null
     },
-    "n_envs": 4,
-    "n_steps": 5,
-    "gamma": 0.99,
-    "gae_lambda": 1.0,
-    "ent_coef": 0.0,
-    "vf_coef": 0.5,
-    "max_grad_norm": 0.5,
-    "normalize_advantage": false
+    "n_envs": 4
 }

a2c-AntBulletEnv-v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aabf5e936e65e164af939d19a86d0220e7e84e4daf34db1e487a42ba12994acb
-size 687
+oid sha256:4fde31676fe5885f611b43ba8c89de9fd92aa0225334f485325c24549073f395
+size 54206

a2c-AntBulletEnv-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5c0cbdb7d9c105bcbffe149c8aa27779f8ce521e74d25a05c722ced33b07ef0
+oid sha256:e7bad288ae762938f2b655a4536bdb4d3eb7a865ca6d7ece8e8ea95ef534c6aa
 size 54910

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 0x7fea30d76b90>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fea30d76c20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fea30d76cb0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fea30d76d40>", "_build": "<function ActorCriticPolicy._build at 0x7fea30d76dd0>", "forward": "<function ActorCriticPolicy.forward at 0x7fea30d76e60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fea30d76ef0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fea30d76f80>", "_predict": "<function ActorCriticPolicy._predict at 0x7fea30d77010>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fea30d770a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fea30d77130>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fea30d771c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fea30d80140>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0008, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuCQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9KNuLrHEMthZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 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, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.1+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 0x7fec5eb0ef80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fec5eb0f010>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fec5eb0f0a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fec5eb0f130>", "_build": "<function ActorCriticPolicy._build at 0x7fec5eb0f1c0>", "forward": "<function ActorCriticPolicy.forward at 0x7fec5eb0f250>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fec5eb0f2e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fec5eb0f370>", "_predict": "<function ActorCriticPolicy._predict at 0x7fec5eb0f400>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fec5eb0f490>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fec5eb0f520>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fec5eb0f5b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fec5eb0aa00>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 2500000, "_total_timesteps": 2500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1686498469881797132, "learning_rate": 0.0005, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuCQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9AYk3S8an8hZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_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:": "gAWVNQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAQAAAAAAAAAAAABz6S+1AACAPwAAAAAAAAAAAAAAAAAAAAAAAACAzJLoPQAAAADos9+/AAAAAJlOnT0AAAAASoXpPwAAAAB8CzY9AAAAAEvp+D8AAAAAXoAnPQAAAABiiuC/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA7sGhNQAAgD8AAAAAAAAAAAAAAAAAAAAAAAAAgDPGmz0AAAAAEt/4vwAAAAAD2UY9AAAAAEC/+j8AAAAAA91UvQAAAADgN+U/AAAAAOpQC74AAAAAKnX8vwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAIQsCjYAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIAwdpg9AAAAAALy978AAAAA57yMPAAAAACfOPE/AAAAAExoczwAAAAAUwP1PwAAAAC2Ywq+AAAAAKYW7r8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABFmhe2AACAPwAAAAAAAAAAAAAAAAAAAAAAAACAp/gCPQAAAABo1/O/AAAAAAPu170AAAAAT9niPwAAAAARyKA9AAAAANwl3j8AAAAAHmcZPQAAAADiPgHAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLHIaUjAFDlHSUUpQu"}, "_episode_num": 0, "use_sde": false, "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": 125000, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.1+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 sha256:776db5314651d849a56dc7af17ec2042231673d0b99b2950df93975bfb13523a
-size 1461389
+oid sha256:565181abb8e67240db35f307d0d74edd02eceae89bfd88206306de86b15c69b0
+size 1112664

results.json

@@ -1 +1 @@
-{"mean_reward": 9.992160886526108, "std_reward": 0.003088249087950704, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-10T22:35:43.769976"}
+{"mean_reward": 2314.725796339661, "std_reward": 78.83391394854095, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-11T17:23:36.829805"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de2e2e6d12f3d260f084ce4c60695b86a1dd9494d9fbfd1c83927ce0c100dbe
+oid sha256:83d900ce6916032745a8fe723375142757ed44f140e0119fa12e73efa6598bf0
 size 2176