Giraffe: Using Deep Reinforcement Learning to Play Chess
This addresses the challenge of reducing human expertise in game AI, though it is incremental as it builds on prior machine learning attempts in chess.
The paper tackles the problem of developing a chess engine with minimal hand-crafted knowledge by using deep reinforcement learning for self-play, achieving performance comparable to state-of-the-art engines that rely on extensive expert tuning.
This report presents Giraffe, a chess engine that uses self-play to discover all its domain-specific knowledge, with minimal hand-crafted knowledge given by the programmer. Unlike previous attempts using machine learning only to perform parameter-tuning on hand-crafted evaluation functions, Giraffe's learning system also performs automatic feature extraction and pattern recognition. The trained evaluation function performs comparably to the evaluation functions of state-of-the-art chess engines - all of which containing thousands of lines of carefully hand-crafted pattern recognizers, tuned over many years by both computer chess experts and human chess masters. Giraffe is the most successful attempt thus far at using end-to-end machine learning to play chess.