Initial commit

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d5c4ecb43b9ca5076a6ed0e2c59adeb7e941975aff82bb9757803aa1de85f06
+oid sha256:2b8d631cd72b036d507722bb261cb53cccdd4663476546ace0db7312cebf2e91
 size 27224794

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 0x7f2da29e7f70>",
+        "__init__": "<function CnnPolicy.__init__ at 0x7f6da8017f70>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f2da29e87b0>"
+        "_abc_impl": "<_abc_data object at 0x7f6da80187b0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -83,12 +83,12 @@
         ":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 0x7f2da2e52ee0>",
-        "add": "<function ReplayBuffer.add at 0x7f2da2e52f70>",
-        "sample": "<function ReplayBuffer.sample at 0x7f2da2e54040>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f2da2e540d0>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f6da8482ee0>",
+        "add": "<function ReplayBuffer.add at 0x7f6da8482f70>",
+        "sample": "<function ReplayBuffer.sample at 0x7f6da8484040>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f6da84840d0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f2da2edcc00>"
+        "_abc_impl": "<_abc_data object at 0x7f6da850dc00>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

results.json

@@ -1 +1 @@
-{"mean_reward": 483.5, "std_reward": 164.89466334602827, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-28T12:33:29.689995"}
+{"mean_reward": 483.5, "std_reward": 164.89466334602827, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-28T12:42:22.522444"}