Home → Magazine Archive → August 2016 (Vol. 59, No. 8) → Reinforcement Renaissance → Abstract

Reinforcement Renaissance

By Marina Krakovsky

Communications of the ACM, Vol. 59 No. 8, Pages 12-14

[article image]

Each time deepmind has announced an amazing accomplishment in game-playing computers in recent months, people have taken notice.

First, the Google-owned, London-based artificial intelligence (AI) research center wowed the world with a computer program that had taught itself to play nearly 50 different 1980s-era Atari games—from Pong and Breakout to Pac-Man, Space Invaders, Boxing, and more—using as input nothing but pixel positions and game scores, performing at or above the human level in more than half these varied games. Then, this January, DeepMind researchers impressed experts with a feat in the realm of strategy games: AlphaGo, their Go-playing program, beat the European champion in the ancient board game, which poses a much tougher AI challenge than chess. Less than two months later, AlphaGo scored an even greater victory: it won 4 games in a best-of-5 series against the best Go player in the world, surprising the champion himself.


No entries found