Giraffe: Using Deep Reinforcement Learning to Play Chess

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.

MSc Dissertation

Cited by in corpus (13)

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
• VAIN: Attentional Multi-agent Predictive Modeling
• Open Problems in Cooperative AI
• Deep Quality-Value (DQV) Learning
• Reconstruction of training samples from loss functions
• Playing Chess with Limited Look Ahead
• A More Human Way to Play Computer Chess
• Growth over time-correlated disorder: a spectral approach to Mean-field
• Exploring the Performance of Deep Residual Networks in Crazyhouse Chess
• SentiMATE: Learning to play Chess through Natural Language Processing
• Deep Pepper: Expert Iteration based Chess agent in the Reinforcement Learning Setting
• Single-step Options for Adversary Driving