COMING SOON! PQDT Open is getting a new home!

ProQuest Open Access Dissertations & Theses will remain freely available as part of a new and enhanced search experience at www.proquest.com.

Questions? Please refer to this FAQ.

Dissertation/Thesis Abstract

Advances in Computer Bridge: Techniques for a Partial-Information, Communication-Based Game
by Bethe, Paul M., Ph.D., New York University, 2021, 97; 28257166
Abstract (Summary)

Bridge is an imperfect information game with elements of competition against opponents as well as cooperation with a partner. Despite the application of many tenets of artificial intelligence, humans have yet to be consistently bested by the computer. This thesis explores AI shortcomings in both the play and bidding phases of the game.In the play, we explore weaknesses in the cutting edge Monte Carlo techniques and explore both inference and learning based solutions.In the bidding, we go beyond existing rule based systems and investigate deep reinforcement learning as a method to learn how to bid.

Indexing (document details)
Advisor: Davis, Ernest
Commitee:
School: New York University
Department: Computer Science
School Location: United States -- New York
Source: DAI-B 82/9(E), Dissertation Abstracts International
Source Type: DISSERTATION
Subjects: Computer science, Artificial intelligence
Keywords: Computer bridge, Computer games
Publication Number: 28257166
ISBN: 9798582575658
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest