Deep Pepper: Expert Iteration based Chess agent in the Reinforcement Learning Setting
This work addresses faster training for chess agents, but appears incremental as it builds on existing self-play methods.
The paper tackles the challenge of training chess-playing agents by introducing Deep Pepper, which uses embedded knowledge to accelerate training compared to tabula rasa systems like AlphaZero, and releases code to support further research.
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.