Heuristic Sampling for Fast Plausible Playouts

C. Browne*, F. Barbero

*Corresponding author for this work

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

62 Downloads (Pure)

Abstract

This paper proposes Heuristic Sampling (HS) for generating self-play trials for games with a defined state evaluation function, with speeds comparable to random playouts but game length estimates comparable to those produced by intelligent AI agents. HS produces plausible results up to thousands of times faster than more rigorous methods.
Original languageEnglish
Title of host publication2021 IEEE CONFERENCE ON GAMES (COG)
PublisherIEEE
Pages1042-1045
Number of pages4
ISBN (Print)9781665438865
DOIs
Publication statusPublished - 2021
EventIEEE Conference on Games (IEEE CoG) - Virtual, Copenhagen, Denmark
Duration: 17 Aug 202121 Aug 2021
https://ieee-cog.org/2021/

Publication series

SeriesIEEE Conference on Computational Intelligence and Games
ISSN2325-4270

Conference

ConferenceIEEE Conference on Games (IEEE CoG)
Country/TerritoryDenmark
CityCopenhagen
Period17/08/2121/08/21
Internet address

Keywords

  • AI
  • Board Games
  • Game Length
  • Ludii
  • SEARCH

Fingerprint

Dive into the research topics of 'Heuristic Sampling for Fast Plausible Playouts'. Together they form a unique fingerprint.

Cite this