Initial commit

ppo-MountainCarContinuous-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c03e1fb65054051f7bd882f881d0bc1c9de057797a17c1dda122f3603344bad
+oid sha256:eece5a8e8380e3b4017d620f622fcef6a3101be28651d44c94ba44deb44ece9d
 size 133332

ppo-MountainCarContinuous-v0/data

@@ -4,20 +4,20 @@
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
-        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f2ecd38a170>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2ecd38a200>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2ecd38a290>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2ecd38a320>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f2ecd38a3b0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f2ecd38a440>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2ecd38a4d0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2ecd38a560>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f2ecd38a5f0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2ecd38a680>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2ecd38a710>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2ecd38a7a0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f4772632170>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4772632200>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4772632290>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4772632320>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f47726323b0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f4772632440>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f47726324d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4772632560>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f47726325f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4772632680>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4772632710>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f47726327a0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f2ecd37fec0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f477263c580>"
     },
     "verbose": 1,
     "policy_kwargs": {

results.json

@@ -1 +1 @@
-{"mean_reward": -1.1606132, "std_reward": 0.052100623107214375, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-17T11:05:04.684534"}
+{"mean_reward": -1.1606132, "std_reward": 0.052100623107214375, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-17T11:06:20.507928"}