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

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.

arXiv commentTabula Rasa, Chess engine, Learning Fast and Slow, Reinforcement Learning, Alpha Zero

References in corpus (7)

• Distilling the Knowledge in a Neural Network
• On the Convergence of Adam and Beyond
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Searching for Activation Functions
• Thinking Fast and Slow with Deep Learning and Tree Search
• Giraffe: Using Deep Reinforcement Learning to Play Chess
• Memory Augmented Control Networks

Cited by in corpus (1)

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