MSc Project Defence: Department of Computer Science - Guðmundur Páll Kjartansson

Experimenting with Time and Depth Control in Chess

  • 25.1.2020, 11:00 - 12:00

Title: Experimenting with Time and Depth Control in Chess
Candidate: Guðmundur Páll Kjartansson
Date and Time: January 25th at 11:00
Location: M121

Abstract: Chess programming has come a long way since 1996 when Deep Blue defeated world champion Garry Kasparov. Deep Blue was the result of many years of labor of knowledge-engineering, where chess-specific features were hand-crafted and carefully hand-tuned. Recently, AlphaZero received worldwide attention for mastering the games of chess, Shogi, and Go through machine-learning and self-play using no game-specific knowledge features (except the rules of the games). In here, we examine ways to improve chess playing programs using machine learning methods. In our first set of experiments, we test whether a neural networks can be trained to determine voilatility of chess positions, i.e. whether they are stable or not, but such information may be used to improve time management. In our second set of experiments, we use regression methods to automatically determine the value of the parameters used in a chess engine for search reductions. We use the world-class program Stockfish for our experiments, and although our experiments did ultimately not lead to improved play, some hold promise, for example, in classifying chess positions as volatile or not.



Vinsamlegast athugið að á viðburðum Háskólans í Reykjavík (HR) eru teknar ljósmyndir og myndbönd sem notuð eru í markaðsstarfi HR. Hægt er að nálgast frekari upplýsingar á ru.is eða með því að senda tölvupóst á netfangið: personuvernd@ru.is
//
Please note that at events hosted at Reykjavik University (RU), photographs and videos are taken which might be used for RU marketing purposes. Read more about this on our ru.is or send an e-mail: personuvernd@ru.is