Initial commit

ppo-QbertNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1083726775fcbca00f9d31928520828c21dc25defe1e0310e41eb309d41e858
+oid sha256:f32ad2bcbe1bff4500bfdd022da1ef73da03ee1c661cf549896e6cfcace17b89
 size 20444874

ppo-QbertNoFrameskip-v4/data

@@ -4,9 +4,9 @@
         ":serialized:": "gAWVPgAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMFEFjdG9yQ3JpdGljQ25uUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    CNN 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 ActorCriticCnnPolicy.__init__ at 0x7fae063e8ee0>",
+        "__init__": "<function ActorCriticCnnPolicy.__init__ at 0x7f34904abee0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fae063eb210>"
+        "_abc_impl": "<_abc_data object at 0x7f34904ac240>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 11515.0, "std_reward": 3534.971711343671, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-14T01:59:05.924442"}
+{"mean_reward": 11515.0, "std_reward": 3534.971711343671, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-14T02:00:34.059793"}