Upload PPO BipedalWalker-v3 trained agent

BipedalWalker-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11538dabe9e23f9b334f8d86141cf750b83aa42942a2c80ac030e16c82dd0d43
-size 173684
+oid sha256:28c6e8ef172da4a89c65875d25b6b16cf29bda756462620f80057a000877800b
+size 173364

BipedalWalker-v3/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 0x7837148a5480>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7837148a5510>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7837148a55a0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7837148a5630>",
-        "_build": "<function ActorCriticPolicy._build at 0x7837148a56c0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7837148a5750>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7837148a57e0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7837148a5870>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7837148a5900>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7837148a5990>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7837148a5a20>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7837148a5ab0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fa01b21db40>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa01b21dbd0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa01b21dc60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa01b21dcf0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fa01b21dd80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fa01b21de10>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa01b21dea0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa01b21df30>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fa01b21dfc0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa01b21e050>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa01b21e0e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa01b21e170>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7837148ac840>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fa01b3c2ec0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,12 +26,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1713750837290831232,
+    "start_time": 1713927914852567191,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,7 +45,7 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
@@ -85,11 +85,11 @@
     "n_envs": 16,
     "n_steps": 300,
     "gamma": 0.999,
-    "gae_lambda": 0.98,
-    "ent_coef": 0.02,
+    "gae_lambda": 0.99,
+    "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "batch_size": 60,
+    "batch_size": 64,
     "n_epochs": 4,
     "clip_range": {
         ":type:": "<class 'function'>",

BipedalWalker-v3/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1448685cdc507703d66cc4b4ec54f8ae6e03d63a8d528889b708e7f1fd6275ec
+oid sha256:8efe1369d3054db90473e3fce641809bd8c1dcf7d26216af9e07bb59322bc6b1
 size 105121

BipedalWalker-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abe0486a3fb629ebe69ccefd0ee4ad7a4f60f90ea0f5b46e2a61c7be1ddd8753
+oid sha256:16683d835b746824c2d4764b46ce347dcdbbcb46596054da74793d22e129cfcd
 size 52143

README.md

@@ -16,7 +16,7 @@ model-index:
       type: BipedalWalker-v3
     metrics:
     - type: mean_reward
-      value: -92.78 +/- 0.06
+      value: -92.20 +/- 0.18
       name: mean_reward
       verified: false
 ---

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 0x7837148a5480>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7837148a5510>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7837148a55a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7837148a5630>", "_build": "<function ActorCriticPolicy._build at 0x7837148a56c0>", "forward": "<function ActorCriticPolicy.forward at 0x7837148a5750>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7837148a57e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7837148a5870>", "_predict": "<function ActorCriticPolicy._predict at 0x7837148a5900>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7837148a5990>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7837148a5a20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7837148a5ab0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7837148ac840>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 4800, "_total_timesteps": 2000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713750837290831232, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -1.4, "_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": 4, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVTAQAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWGAAAAAAAAAABAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLGIWUjAFDlHSUUpSMDWJvdW5kZWRfYWJvdmWUaBEolhgAAAAAAAAAAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBlGgVSxiFlGgZdJRSlIwGX3NoYXBllEsYhZSMA2xvd5RoESiWYAAAAAAAAADbD0nAAACgwAAAoMAAAKDA2w9JwAAAoMDbD0nAAACgwAAAAIDbD0nAAACgwNsPScAAAKDAAAAAgAAAgL8AAIC/AACAvwAAgL8AAIC/AACAvwAAgL8AAIC/AACAvwAAgL+UaAtLGIWUaBl0lFKUjARoaWdolGgRKJZgAAAAAAAAANsPSUAAAKBAAACgQAAAoEDbD0lAAACgQNsPSUAAAKBAAACgQNsPSUAAAKBA2w9JQAAAoEAAAKBAAACAPwAAgD8AAIA/AACAPwAAgD8AAIA/AACAPwAAgD8AAIA/AACAP5RoC0sYhZRoGXSUUpSMCGxvd19yZXBylIz+Wy0zLjE0MTU5MjcgLTUuICAgICAgICAtNS4gICAgICAgIC01LiAgICAgICAgLTMuMTQxNTkyNyAtNS4KIC0zLjE0MTU5MjcgLTUuICAgICAgICAtMC4gICAgICAgIC0zLjE0MTU5MjcgLTUuICAgICAgICAtMy4xNDE1OTI3CiAtNS4gICAgICAgIC0wLiAgICAgICAgLTEuICAgICAgICAtMS4gICAgICAgIC0xLiAgICAgICAgLTEuCiAtMS4gICAgICAgIC0xLiAgICAgICAgLTEuICAgICAgICAtMS4gICAgICAgIC0xLiAgICAgICAgLTEuICAgICAgIF2UjAloaWdoX3JlcHKUjOZbMy4xNDE1OTI3IDUuICAgICAgICA1LiAgICAgICAgNS4gICAgICAgIDMuMTQxNTkyNyA1LiAgICAgICAgMy4xNDE1OTI3CiA1LiAgICAgICAgNS4gICAgICAgIDMuMTQxNTkyNyA1LiAgICAgICAgMy4xNDE1OTI3IDUuICAgICAgICA1LgogMS4gICAgICAgIDEuICAgICAgICAxLiAgICAgICAgMS4gICAgICAgIDEuICAgICAgICAxLiAgICAgICAgMS4KIDEuICAgICAgICAxLiAgICAgICAgMS4gICAgICAgXZSMCl9ucF9yYW5kb22UTnViLg==", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True  True  True  True  True\n  True  True  True  True  True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True  True  True  True  True\n  True  True  True  True  True  True  True  True  True  True  True  True]", "_shape": [24], "low": "[-3.1415927 -5.        -5.        -5.        -3.1415927 -5.\n -3.1415927 -5.        -0.        -3.1415927 -5.        -3.1415927\n -5.        -0.        -1.        -1.        -1.        -1.\n -1.        -1.        -1.        -1.        -1.        -1.       ]", "high": "[3.1415927 5.        5.        5.        3.1415927 5.        3.1415927\n 5.        5.        3.1415927 5.        3.1415927 5.        5.\n 1.        1.        1.        1.        1.        1.        1.\n 1.        1.        1.       ]", "low_repr": "[-3.1415927 -5.        -5.        -5.        -3.1415927 -5.\n -3.1415927 -5.        -0.        -3.1415927 -5.        -3.1415927\n -5.        -0.        -1.        -1.        -1.        -1.\n -1.        -1.        -1.        -1.        -1.        -1.       ]", "high_repr": "[3.1415927 5.        5.        5.        3.1415927 5.        3.1415927\n 5.        5.        3.1415927 5.        3.1415927 5.        5.\n 1.        1.        1.        1.        1.        1.        1.\n 1.        1.        1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 16, "n_steps": 300, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.02, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 60, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"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 0x7fa01b21db40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa01b21dbd0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa01b21dc60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa01b21dcf0>", "_build": "<function ActorCriticPolicy._build at 0x7fa01b21dd80>", "forward": "<function ActorCriticPolicy.forward at 0x7fa01b21de10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa01b21dea0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa01b21df30>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa01b21dfc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa01b21e050>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa01b21e0e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa01b21e170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa01b3c2ec0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 4800, "_total_timesteps": 2000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713927914852567191, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -1.4, "_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": 4, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True  True  True  True  True\n  True  True  True  True  True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True  True  True  True  True\n  True  True  True  True  True  True  True  True  True  True  True  True]", "_shape": [24], "low": "[-3.1415927 -5.        -5.        -5.        -3.1415927 -5.\n -3.1415927 -5.        -0.        -3.1415927 -5.        -3.1415927\n -5.        -0.        -1.        -1.        -1.        -1.\n -1.        -1.        -1.        -1.        -1.        -1.       ]", "high": "[3.1415927 5.        5.        5.        3.1415927 5.        3.1415927\n 5.        5.        3.1415927 5.        3.1415927 5.        5.\n 1.        1.        1.        1.        1.        1.        1.\n 1.        1.        1.       ]", "low_repr": "[-3.1415927 -5.        -5.        -5.        -3.1415927 -5.\n -3.1415927 -5.        -0.        -3.1415927 -5.        -3.1415927\n -5.        -0.        -1.        -1.        -1.        -1.\n -1.        -1.        -1.        -1.        -1.        -1.       ]", "high_repr": "[3.1415927 5.        5.        5.        3.1415927 5.        3.1415927\n 5.        5.        3.1415927 5.        3.1415927 5.        5.\n 1.        1.        1.        1.        1.        1.        1.\n 1.        1.        1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 16, "n_steps": 300, "gamma": 0.999, "gae_lambda": 0.99, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -92.7800962175359, "std_reward": 0.06154593805209314, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-22T01:54:03.938550"}
+{"mean_reward": -92.1980797922799, "std_reward": 0.17525968699805827, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-24T03:05:41.965914"}