Strategic Features for General Games

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

17 Downloads (Pure)

Abstract

This short paper describes an ongoing research project that requires the automated self-play learning and evaluation of a large number of board games in digital form.We describe the approach we are taking to determine relevant features, for biasing MCTS playouts for arbitrary games played on arbitrary
geometries. Benefits of our approach include efficient implementation, the potential to transfer learnt knowledge to new contexts, and the potential to explain strategic knowledge embedded in features in human-comprehensible terms.
Original languageEnglish
Title of host publicationAAAI conference on Artificial Intelligence
Subtitle of host publicationKnowledge Extraction from Games (KEG'19)
Pages71-75
Number of pages5
Publication statusPublished - 27 Jan 2019

Cite this