Learning against learning : evolutionary dynamics of reinforcement learning algorithms in strategic interactions

Michael Kaisers

Research output: ThesisDoctoral ThesisInternal

1346 Downloads (Pure)

Abstract

Imagine computer programs (agents) that learn to coordinate or to compete. This study investigates how their learning processes influence each other. Such adaptive agents already take vital roles behind the scenes of our society, e.g., high frequency automated traders participate in financial trading and create more volume than human trading in some US markets. However, many learning algorithms only have proven performance guarantees if they act alone - as soon as a second agent influences the outcomes most guarantees are invalid. This dissertation extends guarantees to strategic interactions of several agents and examines how closely algorithms approximate optimal behavior.

This research was funded by a TopTalent 2008 grant of NWO.
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • Maastricht University
Supervisors/Advisors
  • Weiss, Gerhard, Supervisor
  • Tuyls, Karl, Co-Supervisor
  • Parsons, S., Co-Supervisor, External person
Award date17 Dec 2012
Place of PublicationMaastricht
Publisher
Print ISBNs9789461693310
DOIs
Publication statusPublished - 1 Jan 2012

Keywords

  • reinforcement learning
  • algorithms
  • strategic interactions

Cite this