AlphaZero: Shedding new light on the grand games of chess, shogi and Go | DeepMind🔒 deepmind.com
The results of AlphaZero are amazing. It’s shocking how quickly it developed winning strategies only using basic rules and playing games against itself and other algorithms.
However, it was the style in which AlphaZero plays these games that players may find most fascinating. In Chess, for example, AlphaZero independently discovered and played common human motifs during its self-play training such as openings, king safety and pawn structure. But, being self-taught and therefore unconstrained by conventional wisdom about the game, it also developed its own intuitions and strategies adding a new and expansive set of exciting and novel ideas that augment centuries of thinking about chess strategy.
I like how this article positions that human players will be able to develop new tactics and strategies by working with AlphaZero. That hybrid human plus algorithm approach will be common in a number of areas in the future, and already is in many. Before readers assume this means AlphaZero can do anything, remember that games are closed-systems with extremely specific rulesets. The world we all occupy is nothing like that.Posted on December 8, 2018 →