Upload PPO HumanoidStandup-v4 trained agent

HumanoidStandup-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7444ef0d22220cbf80cb1228c5904bd576b92f6e08c958cc64fcc2cd783ef56
+size 765837

HumanoidStandup-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

HumanoidStandup-v4/data

@@ -0,0 +1,108 @@
+{
+    "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 0x7c6dbcde7490>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c6dbcde7520>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c6dbcde75b0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c6dbcde7640>",
+        "_build": "<function ActorCriticPolicy._build at 0x7c6dbcde76d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7c6dbcde7760>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c6dbcde77f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c6dbcde7880>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7c6dbcde7910>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c6dbcde79a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c6dbcde7a30>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c6dbcde7ac0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7c6dbcd98800>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1007616,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1723477231094352429,
+    "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:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.007616000000000067,
+    "_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": 1230,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "gAWV9BsAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWeAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlGgIjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiTXgBhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWeAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlGgVTXgBhZRoGXSUUpSMBl9zaGFwZZRNeAGFlIwDbG93lGgRKJbACwAAAAAAAAAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/lGgLTXgBhZRoGXSUUpSMBGhpZ2iUaBEolsALAAAAAAAAAAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H+UaAtNeAGFlGgZdJRSlIwIbG93X3JlcHKUjAQtaW5mlIwJaGlnaF9yZXBylIwDaW5mlIwKX25wX3JhbmRvbZROdWIu",
+        "dtype": "float64",
+        "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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 False False False False False False False False\n False False False False]",
+        "_shape": [
+            376
+        ],
+        "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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf]",
+        "low_repr": "-inf",
+        "high_repr": "inf",
+        "_np_random": null
+    },
+    "action_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]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True  True  True  True  True\n  True  True  True  True  True]",
+        "_shape": [
+            17
+        ],
+        "low": "[-0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4\n -0.4 -0.4 -0.4]",
+        "high": "[0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4]",
+        "low_repr": "-0.4",
+        "high_repr": "0.4",
+        "_np_random": null
+    },
+    "n_envs": 4,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

HumanoidStandup-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c93ca83c9cfb65bc594496b10909d401fb7d532c21eb3d559b0ab078674fc80
+size 472993

HumanoidStandup-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee96f9debc895e00a4fee4c6519e82edb889a451eae8692c6ba1ac42482e4e2
+size 235951

HumanoidStandup-v4/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

HumanoidStandup-v4/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.3.1+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- HumanoidStandup-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: HumanoidStandup-v4
+      type: HumanoidStandup-v4
+    metrics:
+    - type: mean_reward
+      value: 149265.19 +/- 17400.70
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **HumanoidStandup-v4**
+This is a trained model of a **PPO** agent playing **HumanoidStandup-v4**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +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 0x7c6dbcde7490>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c6dbcde7520>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c6dbcde75b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c6dbcde7640>", "_build": "<function ActorCriticPolicy._build at 0x7c6dbcde76d0>", "forward": "<function ActorCriticPolicy.forward at 0x7c6dbcde7760>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c6dbcde77f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c6dbcde7880>", "_predict": "<function ActorCriticPolicy._predict at 0x7c6dbcde7910>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c6dbcde79a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c6dbcde7a30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c6dbcde7ac0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c6dbcd98800>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1007616, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1723477231094352429, "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:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "_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": 1230, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float64", "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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 False False False False False False False False\n False False False False]", "_shape": [376], "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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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\n -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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_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]", "bounded_above": "[ True  True  True  True  True  True  True  True  True  True  True  True\n  True  True  True  True  True]", "_shape": [17], "low": "[-0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4\n -0.4 -0.4 -0.4]", "high": "[0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4]", "low_repr": "-0.4", "high_repr": "0.4", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 149265.19243278503, "std_reward": 17400.696880344847, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-12T16:27:12.632282"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766513355f6bb40b5bfedc309115e2cc0d4e5baf34da4628913d656fcd4dd756
+size 17358