Bigger, Better, Faster: Human-level Atari with human-level efficiency

Max Schwarzer
Johan Obando Ceron
Aaron Courville
Marc Bellemare
ICML (2023)

Abstract

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 moving the goalpost for sample-efficient RL research on the ALE.

Research Areas