Initial commit

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:806d616fa89e92da1764d85bc17360accb36946fc10832bbe6e8f3fe209406ea
+oid sha256:36064871b68b618ee1ff4d8484b5b64165e34a4da260561526c1c7ae31568ec7
 size 13716430

dqn-SpaceInvadersNoFrameskip-v4/data

@@ -4,9 +4,9 @@
         ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCUNublBvbGljeZSTlC4=",
         "__module__": "stable_baselines3.dqn.policies",
         "__doc__": "\n    Policy class for DQN when using images as input.\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 features_extractor_class: Features extractor to use.\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 CnnPolicy.__init__ at 0x7f8989b8d790>",
+        "__init__": "<function CnnPolicy.__init__ at 0x7fb9a62bf790>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f8989b905c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fb9a62c0ac0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -84,12 +84,12 @@
         ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
         "__module__": "stable_baselines3.common.buffers",
         "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
-        "__init__": "<function ReplayBuffer.__init__ at 0x7f8989b6e940>",
-        "add": "<function ReplayBuffer.add at 0x7f8989b6e9d0>",
-        "sample": "<function ReplayBuffer.sample at 0x7f8989b6ea60>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f8989b6eaf0>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7fb9a62a0940>",
+        "add": "<function ReplayBuffer.add at 0x7fb9a62a09d0>",
+        "sample": "<function ReplayBuffer.sample at 0x7fb9a62a0a60>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fb9a62a0af0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f8989b68a80>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fb9a6299fc0>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

results.json

@@ -1 +1 @@
-{"mean_reward": 14.5, "std_reward": 12.338962679253067, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-26T12:50:52.464986"}
+{"mean_reward": 14.5, "std_reward": 12.338962679253067, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-26T13:08:24.611571"}