Initial commit

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff858219dafb82b83432ef4c82d9f7547392fa29ea3393027c66b215cd47915
+oid sha256:5a8faaa2cfd3206c87764d7c9309dbcae32d117028e2d24ff8bad5ad7d204a1a
 size 27220953

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 0x7fc940121990>",
+        "__init__": "<function CnnPolicy.__init__ at 0x7fee95079990>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fc940129d00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fee9507dec0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -84,13 +84,13 @@
         "__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 0x7fc9403fa950>",
-        "add": "<function ReplayBuffer.add at 0x7fc9403fa9e0>",
-        "sample": "<function ReplayBuffer.sample at 0x7fc9403faa70>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fc9403fab00>",
-        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fc9403fab90>)>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7fee9535a950>",
+        "add": "<function ReplayBuffer.add at 0x7fee9535a9e0>",
+        "sample": "<function ReplayBuffer.sample at 0x7fee9535aa70>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fee9535ab00>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fee9535ab90>)>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fc9403f2a80>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fee95352e40>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10251e06dc21515007ee17065072e8e924cfc72893d66ded60e4ccd6c4e41cfc
+size 234651

results.json

@@ -1 +1 @@
-{"mean_reward": 596.5, "std_reward": 123.18786466206808, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-06T17:26:17.412445"}
+{"mean_reward": 596.5, "std_reward": 123.18786466206808, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-06T17:32:10.258156"}