Initial commit

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7d3f7d273576ed976c6db5fd49d9565643dae87d326907ee2369121ac46d88
+oid sha256:98d092b09fd14c1936c3fbdc47e139ef4a7ad1454b11cdaa7bbfb798ac88ef20
 size 27222621

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 0x7f417234a940>",
+        "__init__": "<function CnnPolicy.__init__ at 0x7fc4907ab940>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f417234dfc0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fc4907aefc0>"
     },
     "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:\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    :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 0x7f417232f940>",
-        "add": "<function ReplayBuffer.add at 0x7f417232f9d0>",
-        "sample": "<function ReplayBuffer.sample at 0x7f417232fa60>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f417232faf0>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7fc490790940>",
+        "add": "<function ReplayBuffer.add at 0x7fc4907909d0>",
+        "sample": "<function ReplayBuffer.sample at 0x7fc490790a60>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fc490790af0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f417232b780>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fc49078c780>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1c2844197cc5bfb3a33be0fdf7d9949bb9e6aa6836c58f1a817e1be9a74d86
+size 182795

results.json

@@ -1 +1 @@
-{"mean_reward": 688.0, "std_reward": 388.58847126491025, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-07-08T17:11:04.718774"}
+{"mean_reward": 688.0, "std_reward": 388.58847126491025, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-07-08T17:13:58.430459"}