Closed swsychen closed 5 months ago
This is standard Atari preprocessing. Some games render half their objects during even frames and the other half during odd frames, giving the illusion of a full image to the human player while reducing computational cost for the old Atari 2600 console. Taking mean or max over the last two frames ensures the agent sees a complete image. It should still work without this because Dreamer has memory, but the results would not be as comparable to the prior literature.
Hi, in the embodied/envs/atari.py, I don't get the intention of some parts of the code:
What's the purpose of doing the np.copyto? is it some sort of resetting of the image buffer?
Why we need to do
np.amax
ornp.amean
across the image buffer? Or is there some potential issues if we just use the self.buffers[0]?Could you clarify a bit regarding these points? Thank you very much.