Initial commit

qrdqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f82192c5468c745cfd2cb049ebcf77fb6e068370096f3f62a90c3fbf31b9e46
+oid sha256:066b17cacdebdd6b89c9a9a533eed1561eea3d7b5c475df3f27856b909c4a2ce
 size 38187921

qrdqn-SpaceInvadersNoFrameskip-v4/data

@@ -4,9 +4,9 @@
         ":serialized:": "gAWVLAAAAAAAAACMGnNiM19jb250cmliLnFyZHFuLnBvbGljaWVzlIwJQ25uUG9saWN5lJOULg==",
         "__module__": "sb3_contrib.qrdqn.policies",
         "__doc__": "\n    Policy class for QR-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 n_quantiles: Number of quantiles\n    :param net_arch: The specification of the network architecture.\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 0x177f2e7a0>",
+        "__init__": "<function CnnPolicy.__init__ at 0x28a72a840>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x177f38d80>"
+        "_abc_impl": "<_abc._abc_data object at 0x28a738b40>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -91,13 +91,13 @@
         "__module__": "stable_baselines3.common.buffers",
         "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
         "__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 0x176d1fec0>",
-        "add": "<function ReplayBuffer.add at 0x176d20040>",
-        "sample": "<function ReplayBuffer.sample at 0x176d200e0>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x176d20180>",
-        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x176d20220>)>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x289b23f60>",
+        "add": "<function ReplayBuffer.add at 0x289b240e0>",
+        "sample": "<function ReplayBuffer.sample at 0x289b24180>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x289b24220>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x289b242c0>)>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x176cc0700>"
+        "_abc_impl": "<_abc._abc_data object at 0x289ac4640>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

results.json

@@ -1 +1 @@
-{"mean_reward": 578.0, "std_reward": 134.3726162579266, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-24T01:37:03.608465"}
+{"mean_reward": 578.0, "std_reward": 134.3726162579266, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-24T10:43:27.236379"}