Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 476.00 +/- 251.81
+      value: 554.00 +/- 186.01
       name: mean_reward
       verified: false
 ---
@@ -62,7 +62,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
 
 ## Hyperparameters
 ```python
-OrderedDict([('batch_size', 64),
+OrderedDict([('batch_size', 128),
              ('buffer_size', 100000),
              ('env_wrapper',
               ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 64),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
-             ('n_timesteps', 1000000),
+             ('n_timesteps', 1000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daae59443fe08fd1e328a3e535425763f23755b7acd88197e732f227bf454a70
+oid sha256:494d288623459e06bc3a0714a0fa239b111589b02d2dd229afd407f4856bebe5
 size 27220348

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 0x7fb8d3440ca0>",
+        "__init__": "<function CnnPolicy.__init__ at 0x7fde4dda8d30>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fb8d3436240>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fde4dd9eac0>"
     },
     "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 0x7fb8d3596b90>",
-        "add": "<function ReplayBuffer.add at 0x7fb8d3596c20>",
-        "sample": "<function ReplayBuffer.sample at 0x7fb8d3596cb0>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fb8d3596d40>",
-        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fb8d3596dd0>)>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7fde4e102c20>",
+        "add": "<function ReplayBuffer.add at 0x7fde4e102cb0>",
+        "sample": "<function ReplayBuffer.sample at 0x7fde4e102d40>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fde4e102dd0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fde4e102e60>)>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fb8d378fa40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fde4e114580>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:385ed5f705cfa1be5244b250e52e4e30215765643b4b6423b771adadb0eb9158
-size 199145
+oid sha256:40aa9e213900b18593718f9898e2fed809a68f37849a1c1e2ade76f31bf9f1b9
+size 202996

results.json

@@ -1 +1 @@
-{"mean_reward": 554.0, "std_reward": 186.00806434130752, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-03T18:30:09.731453"}
+{"mean_reward": 554.0, "std_reward": 186.00806434130752, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-03T18:35:51.785686"}