Implementing Propositional Networks on FPGA

Cezary Siwek, Jakub Kowalski, Chiara F. Sironi, Mark H. M. Winands

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

Abstract

The speed of game rules processing plays an essential role in the performance of a General Game Playing (GGP) agent. Propositional Networks (propnets) are an example of a highly efficient representation of game rules. So far, in GGP, only software implementations of propnets have been proposed and investigated. In this paper, we present the first implementation of propnets on Field-Programmable Gate Arrays (FPGAs), showing that they perform between 25 and 58 times faster than a software-propnet for most of the tested games. We also integrate the FPGA-propnet within an MCTS agent, discussing the challenges of the process, and possible solutions for the identified shortcomings.
Original languageEnglish
Title of host publication AI 2018: Advances in Artificial Intelligence.
Place of PublicationCham
PublisherSpringer
Chapter14
Pages133-145
DOIs
Publication statusPublished - 10 Nov 2018

Publication series

SeriesLecture Notes in Computer Science
Volume11320
ISSN0302-9743

Cite this

Siwek, C., Kowalski, J., Sironi, C. F., & Winands, M. H. M. (2018). Implementing Propositional Networks on FPGA. In AI 2018: Advances in Artificial Intelligence. (pp. 133-145). Springer. Lecture Notes in Computer Science, Vol.. 11320 https://doi.org/10.1007/978-3-030-03991-2_14