Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Reinforcement learning produces dominant strategies for the Iterated Prisoner's Dilemma

Harper, Marc, Knight, Vincent, Jones, Martin, Koutsovoulos, Georgios, Glynatsi, Nikoleta and Campbell, Owen 2017. Reinforcement learning produces dominant strategies for the Iterated Prisoner's Dilemma. Plos One 12 (12) , e0188046. 10.1371/journal.pone.0188046

[img]
Preview
PDF - Published Version
Available under License Creative Commons Attribution.

Download (23MB) | Preview

Abstract

We present tournament results and several powerful strategies for the Iterated Prisoner's Dilemma created using reinforcement learning techniques (evolutionary and particle swarm algorithms). These strategies are trained to perform well against a corpus of over 170 distinct opponents, including many well-known and classic strategies. All the trained strategies win standard tournaments against the total collection of other opponents. The trained strategies and one particular human made designed strategy are the top performers in noisy tournaments also.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Advanced Research Computing @ Cardiff (ARCCA)
Mathematics
Publisher: Public Library of Science
ISSN: 1932-6203
Date of First Compliant Deposit: 12 December 2017
Date of Acceptance: 27 October 2017
Last Modified: 25 May 2018 13:57
URI: http://orca.cf.ac.uk/id/eprint/107524

Citation Data

Cited 2 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics