Deep Pepper: Expert Iteration based Chess agent in the Reinforcement Learning Setting

2018/06/02 by G. Vijay Krishna, Kyle Goyette, V., Sai Krishna G. +5 · 1 citation
Computer Science · Economics, Econometrics and Finance · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Games #FOS: Computer and information sciences #Reinforcement Learning in Robotics #Sports Analytics and Performance

paper · pdf · doi:10.48550/arxiv.1806.00683

openalex publication_date 2018/06/02 · openalex created_date 2018/06/13 · openalex updated_date 2026/07/28

Abstract

An almost-perfect chess playing agent has been a long standing challenge in the field of Artificial Intelligence. Some of the recent advances demonstrate we are approaching that goal. In this project, we provide methods for faster training of self-play style algorithms, mathematical details of the algorithm used, various potential future directions, and discuss most of the relevant work in the area of computer chess. Deep Pepper uses embedded knowledge to accelerate the training of the chess engine over a "tabula rasa" system such as Alpha Zero. We also release our code to promote further research.

Citations

• Zur Theorie der Gesellschaftsspiele
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Cited by

• Learning To Navigate The Synthetically Accessible Chemical Space Using\n Reinforcement Learning

Related

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Phoenix: A Self-Optimizing Chess Engine
• Superior Computer Chess with Model Predictive Control, Reinforcement Learning, and Rollout
• Neural Networks for Chess
• Giraffe: Using Deep Reinforcement Learning to Play Chess