Context sensitive reward shaping in a loosely coupled multi-agent system

Yann-Michaël De Hauwere, Sam Devlin, Daniel Kudenko, Ann Nowe

Research output: Chapter in Book/Report/Conference proceedingConference paper

Abstract

Reward shaping is a commonly used approach in single agent reinforcement learning to speed up the learning process. Potential based reward shaping has recently found its way to improve the performance of multi-agent reinforcement learning. Both in single and multi-agent settings these speedups are achieved without losing any theoretical convergence guarantees. This paper describes the use of context aware potential functions in a loosely coupled multi-agent system. In some multi-agent settings, the interactions between the agents only occur sporadically, in certain regions of the state space. It is clear that if speedups through reward shaping are to be achieved, that a different shaping signal should be used in these di?erent regions. We demonstrate how this can be achieved within FCQ-learning, which is an algorithm capable of automatically detecting when agents should take each other into consideration. Coordination problems can even be anticipated before the actual problems occur.
Original languageEnglish
Title of host publicationAdaptive Learning Agents 2012
PublisherAAMAS 2012
Pages73-80
Number of pages8
Publication statusPublished - 5 Jun 2012
Eventthe Adaptive and Learning Agents Workshop - Valencia, Spain
Duration: 5 Jun 2012 → …

Publication series

NameProceedings of the Adaptive and Learning Agents Workshop

Conference

Conferencethe Adaptive and Learning Agents Workshop
Abbreviated titleAAMAS 2012
CountrySpain
CityValencia
Period5/06/12 → …

Keywords

  • Sparse Interactions
  • Reward Shaping

Fingerprint Dive into the research topics of 'Context sensitive reward shaping in a loosely coupled multi-agent system'. Together they form a unique fingerprint.

Cite this