Upload model

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88799f5204b7cda98e37feab9a160fe7ce86b5084cf6f3e9e588da980cd39d99
+oid sha256:3364e1c645fd211be297c6a4c943856cd78e69f65859b5c9f0f50deb3613f2c9
 size 27218718

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 0x7f1e6172c8b0>",
+        "__init__": "<function CnnPolicy.__init__ at 0x7f93c10aa8b0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f1e6172ad00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f93c10ac840>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -83,13 +83,13 @@
         ":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 0x7f1e6170b1f0>",
-        "add": "<function ReplayBuffer.add at 0x7f1e6170b280>",
-        "sample": "<function ReplayBuffer.sample at 0x7f1e6170b310>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f1e6170b3a0>",
-        "_maybe_cast_dtype": "<staticmethod object at 0x7f1e6178b310>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f93c10891f0>",
+        "add": "<function ReplayBuffer.add at 0x7f93c1089280>",
+        "sample": "<function ReplayBuffer.sample at 0x7f93c1089310>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f93c10893a0>",
+        "_maybe_cast_dtype": "<staticmethod object at 0x7f93c110d040>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f1e61705b00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f93c11036c0>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {