Upload PPO BipedalWalker-v3 trained agent

BipedalWalker-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c99fad0e8e751c3f252c2fffdd41c57a1ed4821c7c05359475581fac906af1b
-size 173005
+oid sha256:7a4d0702e184611e78cf370b25feca519e76c33fb3cb25161cf994050f776ad6
+size 173325

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 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>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x783b7dbb27a0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x783b7dbb2830>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x783b7dbb28c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x783b7dbb2950>",
+        "_build": "<function ActorCriticPolicy._build at 0x783b7dbb29e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x783b7dbb2a70>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x783b7dbb2b00>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x783b7dbb2b90>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x783b7dbb2c20>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x783b7dbb2cb0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x783b7dbb2d40>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x783b7dbb2dd0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fa01b3c2ec0>"
+        "_abc_impl": "<_abc._abc_data object at 0x783b7db57600>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,12 +26,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1713928871380333681,
+    "start_time": 1714022747756011012,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdQYAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYABgAAAAAAAOocHT5dMyG9LAoEvYpB0TqGRJE/AACAMgJVYT9FgO6+AAAAAMl3Qb/+/38/fC/ZvnXg7b0AAAAActaBPutPgz5m6Ic+RjGQPqRQnT4Gc7E+jN/QPrR4Aj8hKDM/AACAP4zwPT7mrz08mTR8PXaCDD2gi1a//EY9vIDxNL67ooA/AAAAABZHkT8Ai705W1QaP3xxSb4AAAAAi1RsPp4Dbz4KYXc+ujqDPhUsjz4Uf6E+ZBi+PuJ77T7kDCM/AACAP12CMz4tTym9SnLnPe+zSL09M5A/ACAiOiRXZj8NAoA/AAAAAItpUr8AgMq3eBkgv4BLmbsAAAAAB5V5PqBqfD4QoII+gZaKPkwzlz5Wjao+LsHIPu7M+j50MSw/AACAP7ZsqD7x6Q89B14RPSy9pbxaeVK/AAAAtFBWDb8BAIC/AAAAAKy6Rj9K4nm/7iZsP8havz8AAIA/DFCDPs/NhD6nc4k+n9SRPiganz4Xd7M+AT/TPib0Az8qMTU/AACAP9NjCT7swa084vEEvKoCxDx0Cos/AAAAALy/Yz+12nW+AACAPwq/L79RL0A/kGeXvel8Hb8AAIA/bZiCPhoUhD5ys4g+swiRPq07nj4jfLI+nBfSPqI7Az/LMzQ/AACAPx6PiL1utme8NcB1PWrQPD0yMq++uPu8PmA+Ur6JJYC/AACAP0V7kT8AAEi27BZxP8CNODwAAIA/bQyHPgyViD6+XI0+vPqVPu6goz4tkrg+jkHZPjK1Bz/TWDo/AACAP+3vUz4E2fy7WLsKvdwpDDvHFVS/0Ntju5hxzT2ILw09AACAP4l9hT9Lfnm+XC1tP1XVuzcAAAAAXw1zPvzPdT5Ran4+RPaGPpY+kz4CF6Y+kIDDPh099D4isCc/AACAPy+vXD7/1VG9V6aNPTtS7Lyqx0y/tK7JPWB2Ur5XKoA/AACAPwd3fz8cz0w+Mg9ZP9EJgD8AAAAAkdZ3Phinej5mtoE+mJ6JPtQklj4/XKk+EFrHPkoM+T5u/So/AACAP05S0D7XzH49jvQVPjxaiD2qRJE/AICMunTptj7pAYC/AAAAAC7y7r4+qla/tP0Ov/KCmT4AAIA/NJ6RPo5Fkz4FbZg+qrehPlRvsD4qBMc+aULqPi9UEj9m7kg/AACAPxlAnj3b7Ne8pC6cPSr+rbuc9Um/X6hmv4pWHr8AAAAAAAAAAFzciz/u27W9gIFxP58YZz8AAIA/zS9wPhbqcj50ans+7l6FPi6CkT65IaQ+gTLBPvZb8T4GtiU/AACAP9ktAz+vNFS9xasoPkNYgLvlh1C/gJhEPIjw/77FxH4/AACAPywEUj/ISYC/dqyxPlcxfz8AAAAAFN2HPhJoiT4nN44+deKWPr2dpD5Xr7k+OJHaPt6GCD+8eDs/AACAPxW1qj5vzB28689SPDNrer1qPYc/mc9tPq7LBT8BAIC/AAAAADyuU78AAAAAMNwVv/3/f78AAAAARyeGPkythz7ibIw+QfyUPkqLoj4AWbc+69DXPu7OBj+iHDk/AACAPwTPEz63t1c9xE5dPYh1mjw4vVW/AAANOeDWVb4VEnC+AAAAALDmjz8AAE238H05P+YyB78AAIA/jzZrPmLibT6vNXY+7JuCPtV+jj6nu6A+WzK9PoFc7D6VRyI/AACAP6bv3D4KFp686Yydvc+ABrw2llE/0N4ZPxt4QD8AAIC/AAAAAEIfTb8AAAAAfOrcvsi5vr4AAAAAcYiLPhoejT5uDpI+rfWaPuYPqT4rs74+oTHfPtSGDj8njj0/AACAPzNm+D7T9MQ8W3KpvSqfnzoRG2Q/7yyAv2BjwT6BpXs/AACAPyXDTb+6Dza9aEfTvuoHgL8AAIA/3ZSLPqoqjT5vG5I+eQObPvMeqT4mxL4+YozgPk1DDD/QjEA/AACAP5mkAT7xaQg99ndPvBOwMD2YRFW/AEeXOkCWj77USnS/AACAP6s9jz8AkCm4Ak5LPzMNyb4AAIA/F31mPi4baT6sQ3E+qfh/Ph6iiz4pgZ0+gWW5PiGd5z4jBR8/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLEEsYhpSMAUOUdJRSlC4="
+        ":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'>",

BipedalWalker-v3/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40aac6236762b50c17cea3b9a5f05d313b3f2c34a043718919af81d8b58ba75
+oid sha256:8a7e8bc42784ccbfbcd118cea6311c7f9413a5d53c79ef8a9e01efad2594f102
 size 105121

BipedalWalker-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18a982688dc3b89be0b3319695485758b12098a09a528704a700c178801b12e2
+oid sha256:5c895e264373f2e0d208fde78d2d1d6fff3d16e098516f71b641048a8b8ced28
 size 52143

README.md

@@ -16,7 +16,7 @@ model-index:
       type: BipedalWalker-v3
     metrics:
     - type: mean_reward
-      value: -21.83 +/- 47.14
+      value: -92.28 +/- 0.07
       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 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": 1713928871380333681, "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:": "gAWVCAIAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwFyjJzkp7TmMAWyUSyqMAXSUR0AYX8xbjcVQdX2UKGgGR8BbVG6oVEeAaAdLLGgIR0AYaeSSvC/HdX2UKGgGR8BZbGS2Yv38aAdLMGgIR0AYhR/EwWWQdX2UKGgGR8BacWipNsWPaAdLMWgIR0AYjpwCKaXsdX2UKGgGR8BbxUlJHy3DaAdLM2gIR0AYp5prULDydX2UKGgGR8BaySDdxhlUaAdLO2gIR0AY1m7J4jbBdX2UKGgGR8BbO8w1zhgmaAdLQGgIR0AY+rT6SDAadX2UKGgGR8BeloZQ53kgaAdLTmgIR0AZT/dZaFEidX2UKGgGR8Bavh7VrhzeaAdLSGgIR0AaNzgdfb9IdX2UKGgGR8BeIlLeyiVTaAdLSmgIR0AaUzbeuV5bdX2UKGgGR8BewOY2Kl54aAdLSGgIR0AafozN2TxHdX2UKGgGR8BYcg5eZ5RkaAdLV2gIR0AawzzmOlwcdX2UKGgGR8BdJQLE1l5GaAdLUGgIR0AbAK/mDDjzdX2UKGgGR8BZJ07fYSQHaAdLPmgIR0Ab5EE1VHWjdX2UKGgGR8BZEUQGwA2iaAdLOmgIR0AcOEi+tbLVdX2UKGgGR8BZs9qL0jC6aAdLPmgIR0AdaGvfTCtSdWUu"}, "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": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "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:": "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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"}}
+{"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 0x783b7dbb27a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x783b7dbb2830>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x783b7dbb28c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x783b7dbb2950>", "_build": "<function ActorCriticPolicy._build at 0x783b7dbb29e0>", "forward": "<function ActorCriticPolicy.forward at 0x783b7dbb2a70>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x783b7dbb2b00>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x783b7dbb2b90>", "_predict": "<function ActorCriticPolicy._predict at 0x783b7dbb2c20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x783b7dbb2cb0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x783b7dbb2d40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x783b7dbb2dd0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x783b7db57600>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 4800, "_total_timesteps": 2000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1714022747756011012, "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": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "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:": "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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": -21.82893384314648, "std_reward": 47.13824005008511, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-24T03:21:48.820325"}
+{"mean_reward": -92.28305220068141, "std_reward": 0.07317789411062775, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-25T05:27:06.439335"}