Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

5 Dec 2017David SilverThomas HubertJulian SchrittwieserIoannis AntonoglouMatthew LaiArthur GuezMarc LanctotLaurent SifreDharshan KumaranThore GraepelTimothy LillicrapKaren SimonyanDemis Hassabis

The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Game of Go ELO Ratings AlphaGo Zero ELO Rating 5185 # 1
Game of Shogi ELO Ratings AlphaZero ELO Rating 4650 # 1