Initial Commit

README.md

@@ -51,6 +51,8 @@ python -m utils.push_to_hub --algo a2c --env BreakoutNoFrameskip-v4 -f logs/ -or
 ## Hyperparameters
 ```python
 OrderedDict([('ent_coef', 0.01),
+             ('env_wrapper',
+              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
              ('frame_stack', 4),
              ('n_envs', 16),
              ('n_timesteps', 10000000.0),

a2c-BreakoutNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a9cb4161285c58f89baafe730bb8ddef22a7e94bbc37f2aa574b0c3e770bcb
+oid sha256:7950c49d4750a25a27427b37c94999e4d58fbd26bf1683c8f39f31b609f9502c
 size 13674198

a2c-BreakoutNoFrameskip-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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f373dd1a0e0>",
+        "__init__": "<function ActorCriticCnnPolicy.__init__ at 0x7f13821b60e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f373dd7b9f0>"
+        "_abc_impl": "<_abc_data object at 0x7f13822179f0>"
     },
     "verbose": 1,
     "policy_kwargs": {

results.json

@@ -1 +1 @@
-{"mean_reward": 349.5, "std_reward": 89.73878760045736, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-05-20T10:05:42.227623"}
+{"mean_reward": 349.5, "std_reward": 89.73878760045736, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-05-20T10:11:15.299314"}