Mr. Slab Chess Engine

Authors

Nicholas Myer '23, DePauw University

Document Type

Abstract

Publication Date

5-1-2023

Abstract

Mr. Slab is a chess program based in Python that trained itself using the evaluations of another chess program, Stockfish 15, and convolutional neural networking. Inspired by AI research company DeepMind’s AlphaZero chess engine, Mr. Slab learned to play chess starting from nothing but knowing the rules of the game. Mr. Slab’s first games demonstrated no understanding of chess or strategical direction, but as the program evolved to recognize patterns it improved with every iteration. Mr. Slab shows significant improvement in chess ability after training on a database of chess games.

Comments

Completed as part of the Computer Science Senior Capstone Project.

Recommended Citation

Myer, Nicholas '23, "Mr. Slab Chess Engine" (2023). Student Research. 302, Scholarly and Creative Work from DePauw University.
https://scholarship.depauw.edu/studentresearchother/302