Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 94.28 +/- 93.50
+      value: 1603.84 +/- 154.93
       name: mean_reward
       verified: false
 ---

a2c-AntBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca160310d0461ec87898a3f2ef8bcec6031caa34fe231ccc38d190954f899ad
-size 67337
+oid sha256:cc4920975909bcd059e186ec9ce63a355e22c76758bb049a6e0c3c37f988a5de
+size 129248

a2c-AntBulletEnv-v0/data

@@ -32,32 +32,54 @@
             "weight_decay": 0
         }
     },
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 2000000,
+    "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
+    "start_time": 1687110957433905464,
     "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,
+    "_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,
+    "_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": 62500,
+    "n_steps": 8,
+    "gamma": 0.99,
+    "gae_lambda": 0.9,
+    "ent_coef": 0.0,
+    "vf_coef": 0.4,
+    "max_grad_norm": 0.5,
+    "normalize_advantage": false,
     "observation_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             28
@@ -70,7 +92,7 @@
     },
     "action_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             8
@@ -81,12 +103,5 @@
         "bounded_above": "[ True  True  True  True  True  True  True  True]",
         "_np_random": null
     },
-    "n_envs": 4,
-    "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
+    "n_envs": 4
 }

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:bd364162a7a41accb8498fa4d157359c9629e154e4907f84af8c8faf753d4326
+size 56190

a2c-AntBulletEnv-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f196edb3f467e4c86fb22afb7c064c55fd0c412b9976336895bfd9ba9d7d8799
+oid sha256:0db8d7b504e573f9f88920315f397a978bbcd368524a14366049bbb57e827089
 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 0x7f2a47041240>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2a470412d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2a47041360>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2a470413f0>", "_build": "<function ActorCriticPolicy._build at 0x7f2a47041480>", "forward": "<function ActorCriticPolicy.forward at 0x7f2a47041510>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2a470415a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2a47041630>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2a470416c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2a47041750>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2a470417e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2a47041870>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f2a470336c0>"}, "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": 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, "_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": 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-5.15.107+-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 0x7f2a47041240>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2a470412d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2a47041360>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2a470413f0>", "_build": "<function ActorCriticPolicy._build at 0x7f2a47041480>", "forward": "<function ActorCriticPolicy.forward at 0x7f2a47041510>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2a470415a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2a47041630>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2a470416c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2a47041750>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2a470417e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2a47041870>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f2a470336c0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 2000000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1687110957433905464, "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:": "gAWVRAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQJ1gIaQ3gk2MAWyUTegDjAF0lEdAqi8PWrfce3V9lChoBkdAmRILcXWOImgHTegDaAhHQKovooaUA1h1fZQoaAZHQJmWjJjlPrRoB03oA2gIR0CqNNUSRKYidX2UKGgGR0CXBUbNr0rcaAdN6ANoCEdAqjW4NsnAqXV9lChoBkdAm5BqFmFrVWgHTegDaAhHQKo7KLNwBHV1fZQoaAZHQJvJXp/wy7BoB03oA2gIR0CqO8efRNRFdX2UKGgGR0CZ9B2Ifr8jaAdN6ANoCEdAqkE216Vt43V9lChoBkdAiJ1zSkTHsGgHTegDaAhHQKpCFfxc3VF1fZQoaAZHQJszx3FDOTtoB03oA2gIR0CqSgxeTmnwdX2UKGgGR0CaxfUCJXQuaAdN6ANoCEdAqksGrsByS3V9lChoBkdAhIgoZIg/1WgHTegDaAhHQKpRPFWn0kJ1fZQoaAZHQJ28AmTkhidoB03oA2gIR0CqUhMjNY8udX2UKGgGR0CdMFV81Gb1aAdN6ANoCEdAqldOViWmg3V9lChoBkdAm9j3l0YCQ2gHTegDaAhHQKpX6495hSd1fZQoaAZHQJ7kNMEidJ9oB03oA2gIR0CqXT87p3X7dX2UKGgGR0CRcqsU7CBPaAdN6ANoCEdAql4cSIxgzHV9lChoBkdAnWZ8/t6X0GgHTegDaAhHQKpkahpxm051fZQoaAZHQJj3JhLGrCFoB03oA2gIR0CqZUHqmj0udX2UKGgGR0CXXTFUQ04zaAdN6ANoCEdAqm0Mb70nPXV9lChoBkdAlySOPq9oOGgHTegDaAhHQKpt6RV6u4h1fZQoaAZHQJRayDbrTphoB03oA2gIR0Cqc1fZM+NcdX2UKGgGR0CbI00dRzikaAdN6ANoCEdAqnPzqbBoEnV9lChoBkdAnWVrV8Ti82gHTegDaAhHQKp5Sre67NB1fZQoaAZHQJY56MBIWgxoB03oA2gIR0Cqei/iHZbqdX2UKGgGR0CUXekj5bhWaAdN6ANoCEdAqn/mcriEQHV9lChoBkdAjFiVPnB+F2gHTegDaAhHQKqAg1yeZoh1fZQoaAZHQIOwZD3M6iloB03oA2gIR0CqiKajnFHbdX2UKGgGR0CP3U57w8W9aAdN6ANoCEdAqooHJkoWpXV9lChoBkdAgkCHCoCMgmgHTegDaAhHQKqP2qaw2VF1fZQoaAZHQJ2Fo1ivxH5oB03oA2gIR0CqkHrtmcvvdX2UKGgGR0CeNA1OCXhPaAdN6ANoCEdAqpW5HAh0Q3V9lChoBkdAjbLbALy+YmgHTegDaAhHQKqWn6v7m+11fZQoaAZHQIZrEKNQ0oBoB03oA2gIR0CqnABhpg1FdX2UKGgGR0CYEcOxB3RpaAdN6ANoCEdAqpyVNDc/MXV9lChoBkdAlZES5RTCL2gHTegDaAhHQKqi4QPqcEx1fZQoaAZHQJ7Vj0cwQDpoB03oA2gIR0CqpCMhX8wYdX2UKGgGR0CfP+FglWwNaAdN6ANoCEdAqquSi0v4/XV9lChoBkdAmeIAIt16mmgHTegDaAhHQKqsLHMlkYp1fZQoaAZHQJ2iCkoF3ZBoB03oA2gIR0CqsVJwKjSHdX2UKGgGR0Cd2FSVnmJWaAdN6ANoCEdAqrIsG7jDK3V9lChoBkdAntfkhNdqtmgHTegDaAhHQKq3bd0JWvN1fZQoaAZHQJ0PRJyyUs5oB03oA2gIR0CquAOOCGvfdX2UKGgGR0CbMdaEi+tbaAdN6ANoCEdAqr1EUO/cnHV9lChoBkdAntXJgkTpPmgHTegDaAhHQKq+RCBPKuB1fZQoaAZHQJx8AFFDv3JoB03oA2gIR0Cqxk+j/MnrdX2UKGgGR0Cc8S5aePJaaAdN6ANoCEdAqsdEw5/9YXV9lChoBkdAmVmSJj2Ba2gHTegDaAhHQKrNAsA/9pB1fZQoaAZHQJUT4fQrtmdoB03oA2gIR0Cqzd/W1+iKdX2UKGgGR0CJPcacZtN0aAdN6ANoCEdAqtNAqRU3oHV9lChoBkdAmIvvCVKPGWgHTegDaAhHQKrT105lvqF1fZQoaAZHQJOkbxNIsiBoB03oA2gIR0Cq2RoFNcnmdX2UKGgGR0CZUug0TDfnaAdN6ANoCEdAqtn1f1Hvt3V9lChoBkdAkKMwGW2PUGgHTegDaAhHQKrg4eEqUeN1fZQoaAZHQIOFHxWkrPNoB03oA2gIR0Cq4d/rjYI0dX2UKGgGR0CHT1CP6sQvaAdN6ANoCEdAqulFAPd2xXV9lChoBkdAlh6TsyBTXWgHTegDaAhHQKrqJpB5X2d1fZQoaAZHQIipMNDtw71oB03oA2gIR0Cq75zAN5MUdX2UKGgGR0CT4/lSS/0vaAdN6ANoCEdAqvA4PK+zt3V9lChoBkdAmRWpPM0P6WgHTegDaAhHQKr1bbg0j1R1fZQoaAZHQJqTOecx0uFoB03oA2gIR0Cq9kdTo+wDdX2UKGgGR0CYKwzC1qnFaAdN6ANoCEdAqvvmzlcQiHV9lChoBkdAmIPckUsWf2gHTegDaAhHQKr8w4kNWlx1fZQoaAZHQJwEkJIDoyNoB03oA2gIR0CrBIIXsPatdX2UKGgGR0CbAkt65XlsaAdN6ANoCEdAqwXRZjhDPXV9lChoBkdAm869wWFewGgHTegDaAhHQKsLLPrOZ9d1fZQoaAZHQJ30pTvRZ2ZoB03oA2gIR0CrC8TR6WxAdX2UKGgGR0CYsuBun/DMaAdN6ANoCEdAqxD2b3Gn43V9lChoBkdAm1I0puuRtGgHTegDaAhHQKsRyobXHzZ1fZQoaAZHQJwgs45tFa1oB03oA2gIR0CrFyDpTuOTdX2UKGgGR0CcTjcOskpraAdN6ANoCEdAqxfCYG+sYHV9lChoBkdAnHMWJN0vG2gHTegDaAhHQKseV0I1LrZ1fZQoaAZHQJm0a51/2CdoB03oA2gIR0CrH6InrpqzdX2UKGgGR0Cbz+5M10koaAdN6ANoCEdAqyaoH9m6G3V9lChoBkdAl0l0w8GLUGgHTegDaAhHQKsnR3Dej211fZQoaAZHQJ1iKMefZmJoB03oA2gIR0CrLJdmpVCHdX2UKGgGR0CUeyegte2NaAdN6ANoCEdAqy14yTINmXV9lChoBkdAlu8gLApKBmgHTegDaAhHQKsyz/ACW/t1fZQoaAZHQJz1k3cYZVJoB03oA2gIR0CrM3f7rLQpdX2UKGgGR0CcMMsRg7YDaAdN6ANoCEdAqzjnOdGy5nV9lChoBkdAn5ijR6Ww/2gHTegDaAhHQKs6HgHeJpF1fZQoaAZHQJd2KdkJ8fFoB03oA2gIR0CrQjyvLX+VdX2UKGgGR0CccXa9K28aaAdN6ANoCEdAq0MmRYA80XV9lChoBkdAnW1zv7WNFWgHTegDaAhHQKtIWu5jH4p1fZQoaAZHQJ296USqU/xoB03oA2gIR0CrSTUdq+JxdX2UKGgGR0CdlOOC5EtvaAdN6ANoCEdAq06JhBqsVHV9lChoBkdAnD5fI4lyBGgHTegDaAhHQKtPI2phnap1fZQoaAZHQJvPw4xUNrloB03oA2gIR0CrVGo6Kcd6dX2UKGgGR0CbJG5t3wCsaAdN6ANoCEdAq1VJe7cwg3V9lChoBkdAlM9owM6RyWgHTegDaAhHQKtcbkqc3ER1fZQoaAZHQJpwzWwu/URoB03oA2gIR0CrXWACfYjCdX2UKGgGR0Cao1ghbGFSaAdN6ANoCEdAq2Rgksz2vnV9lChoBkdAllT+ogmqpGgHTegDaAhHQKtlOTFERap1fZQoaAZHQJi2LY8Md95oB03oA2gIR0CrarDujRD1dX2UKGgGR0CTjJPIGQjmaAdN6ANoCEdAq2tJZfUnX3V9lChoBkdAmnrU0Nz8xmgHTegDaAhHQKtwajFAE+x1fZQoaAZHQJuUu8XenAJoB03oA2gIR0CrcU5VfeDWdX2UKGgGR0CbBMA7gbZOaAdN6ANoCEdAq3bjNKRMe3V9lChoBkdAmtCxlg+hXmgHTegDaAhHQKt3tWsA/9p1fZQoaAZHQJ1ryLzf779oB03oA2gIR0Crf6FeF+NMdX2UKGgGR0CbX0W8yvcKaAdN6ANoCEdAq4DjfzjFQ3VlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 62500, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVbQIAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLHIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWcAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lGgLSxyFlIwBQ5R0lFKUjARoaWdolGgTKJZwAAAAAAAAAAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH+UaAtLHIWUaBZ0lFKUjA1ib3VuZGVkX2JlbG93lGgTKJYcAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLHIWUaBZ0lFKUjA1ib3VuZGVkX2Fib3ZllGgTKJYcAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUaCJLHIWUaBZ0lFKUjApfbnBfcmFuZG9tlE51Yi4=", "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"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 94.27935626059771, "std_reward": 93.49616737400002, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-18T17:00:28.122227"}
+{"mean_reward": 1603.839006034145, "std_reward": 154.92934793236063, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-18T18:55:18.726393"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efb4be7deded975e3116968c5a679c87b80694b3715bb59dd3642b5d1474f070
+oid sha256:21932217edc39a4a9121b1a4bbee161a1fd27421b1544e5868bb6241b0a00b2f
 size 2176