Human Learning in Atari

TitleHuman Learning in Atari
Publication TypeReport
Year of Publication2017
AuthorsTsividis, P, Pouncy, T, Xu, JL, Tenenbaum, JB, Gershman, SJ

Atari games are an excellent testbed for studying intelligent behavior, as they offer a range of tasks that differ widely in their visual representation, game dynamics, and goals presented to an agent. The last two years have seen a spate of research into artificial agents that use a single algorithm to learn to play these games. The best of these artificial agents perform at better-than-human levels on most games, but require hundreds of hours of game-play experience to produce such behavior. Humans, on the other hand, can learn to perform well on these tasks in a matter of minutes. In this paper we present data on human learning trajectories for several Atari games, and test several hypotheses about the mecha- nisms that lead to such rapid learning. 

Download:  PDF icon Tsividis et al - Human Learning in Atari.pdf

Research Area: 

CBMM Relationship: 

  • CBMM Funded