AI Hub
All papers
Reinforcement Learning

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

DeepMind·December 5, 2017

David Silver, Thomas Hubert, Julian Schrittwieser

View on arXiv

TL;DR

AlphaZero masters chess, shogi, and Go from self-play alone, with no human game data.

Why it matters

A striking demonstration of general reinforcement learning, learning superhuman play from scratch.

Related models

Related terms