HackerPapers

arXiv:1707.06307cs.GT

Reinforcement Learning Produces Dominant Strategies for the Iterated Prisoner's Dilemma

Marc Harper, Vincent Knight, Martin Jones, Georgios Koutsovoulos, Nikoleta E. Glynatsi, Owen Campbell

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

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.

arXiv comments
Journal reference
DOI
doi:10.1371/journal.pone.0188046
Subjects
cs.GTComputer Science and Game Theory

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Aug 2017 to Aug 2017.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. 'Snowdrift' game tops 'Prisoner's Dilemma' in explaining cooperation (2007) 1 comment

    • The Axelrod library is a Python implementation of the Prisoner's dilemma (tournaments, evolutionary dynamics etc) with over 200 strategies. It can also be used to study other games (http://axelrod.readthedocs.io/en/stable/tutorials/advanced/g...) so it would be straightforward…

      drvinceknightView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.