Skip to yearly menu bar Skip to main content


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

Max Schwarzer · Johan Obando Ceron · Aaron Courville · Marc Bellemare · Rishabh Agarwal · Pablo Samuel Castro

Exhibit Hall 1 #229


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

Chat is not available.