Skip navigation
Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp016t053k07c
Title: Playing Connect6 With Threat Space Search And Temporal Difference Learning
Authors: Yuan, Matthew
Advisors: E, Weinan
Department: Mathematics
Class Year: 2021
Abstract: In this paper we combine threat space search (TSS) and temporal difference (TD) learning to create three bots for the board game Connect6. By using TD learning to train a novel evaluation function based on a neural network, our best bot, Bryony, performs better than 89% of all Connect6 players on the board game website Little Golem (littlegolem.net).
URI: http://arks.princeton.edu/ark:/88435/dsp016t053k07c
Type of Material: Princeton University Senior Theses
Language: en
Appears in Collections:Mathematics, 1934-2021

Files in This Item:
File Description SizeFormat 
YUAN-MATTHEW-THESIS.pdf461.02 kBAdobe PDF    Request a copy


Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.