Deep Learning for Real-Time Atari Game Play

Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning

Guo et al. 2014

The combination of modern Reinforcement Learning and Deep Learning approaches holds the promise of making significant progress on challenging applications requiring both rich perception and policy-selection. The Arcade Learning Environment (ALE) provides a set of Atari games that represent a useful bench-mark set of such applications.