Open TianQingX opened 1 month ago
Hi, this is not an error. The Atari tasks are recommended to be run on a GPU rather than a CPU. If you want to test the Atari tasks with CPU, you can reduce the number of parallel environments, buffer size and test_episode in configuration files.
python benchmark.py Calculating device: cpu Deep learning toolbox: PyTorch. Algorithm: DQN Environment: Atari Scenario: Breakout-v4 A.L.E: Arcade Learning Environment (version 0.7.5+db37282) [Powered by Stella] /home/pillar/anaconda3/envs/xuance_env/lib/python3.7/site-packages/gym/utils/passive_env_checker.py:32: UserWarning: WARN: A Box observation space has an unconventional shape (neither an image, nor a 1D vector). We recommend flattening the observation to have only a 1D vector or use a custom policy to properly process the data. Actual observation shape: (210, 160) "A Box observation space has an unconventional shape (neither an image, nor a 1D vector). "
请问什么版本才有breakoutv5, 当前版本运行会如下有报错