We introduce a value-based RL agent, which we call BBF, that achieves super-human performance in the Atari 100K benchmark. BBF relies on scaling the neural networks used for value estimation, as well as a number of other design choices that enable this scaling in a sample-efficient manner. We conduct extensive analyses of these design choices and provide insights for future work. We end with a discussion about updating the goalposts for sample-efficient RL research on the ALE. We make our code and data publicly available at https://github.com/google-research/google-research/tree/master/bigger_better_faster.
@article{arxiv.2305.19452,
title = {Bigger, Better, Faster: Human-level Atari with human-level efficiency},
author = {Max Schwarzer and Johan Obando-Ceron and Aaron Courville and Marc Bellemare and Rishabh Agarwal and Pablo Samuel Castro},
journal= {arXiv preprint arXiv:2305.19452},
year = {2023}
}