Initial commit

ppo-MiniGrid-Unlock-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa9364cc8670212fa1288dcc81a409f44bf8466a4d4e3756775a8ce09b58bc1c
+oid sha256:c054597493091746bf301c002409f205bb090bb08880f3ba540395a1594c67e3
 size 4390837

ppo-MiniGrid-Unlock-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 0x7fc060194040>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc0601940d0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc060194160>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc0601941f0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fc060194280>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fc060194310>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc0601943a0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc060194430>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fc0601944c0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc060194550>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc0601945e0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc060194670>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f20514d4040>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f20514d40d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f20514d4160>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f20514d41f0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f20514d4280>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f20514d4310>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f20514d43a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f20514d4430>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f20514d44c0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f20514d4550>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f20514d45e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f20514d4670>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fc060196040>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f2051a7dcc0>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 0.7671875000000001, "std_reward": 0.38382391898011, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-31T12:43:51.065415"}
+{"mean_reward": 0.7671875000000001, "std_reward": 0.38382391898011, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-31T18:23:50.325074"}