Giraffe: Using Deep Reinforcement Learning to Play Chess

TL;DR

Giraffe is a chess engine that employs deep reinforcement learning with minimal human input, automatically learning features and patterns to achieve performance comparable to traditional, expert-tuned engines.

Contribution

This work introduces Giraffe, the first successful end-to-end machine learning chess engine that automatically learns evaluation features through self-play.

Findings

Giraffe's evaluation function performs comparably to state-of-the-art engines.

It uses minimal hand-crafted knowledge, relying mainly on learned features.

Giraffe demonstrates the potential of deep reinforcement learning in complex strategic games.

Abstract

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.