AN EMPIRICAL STUDY OF POTENTIAL-BASED REWARD SHAPING AND ADVICE IN COMPLEX, MULTI-AGENT SYSTEMS

Sam Devlin (), Daniel Kudenko () and Marek Grześ ()
Additional contact information
Sam Devlin: University of York, UK
Daniel Kudenko: University of York, UK
Marek Grześ: University of Waterloo, CA, Canada

Advances in Complex Systems (ACS), 2011, vol. 14, issue 02, 251-278

Abstract: This paper investigates the impact of reward shaping in multi-agent reinforcement learning as a way to incorporate domain knowledge about good strategies. In theory, potential-based reward shaping does not alter the Nash Equilibria of a stochastic game, only the exploration of the shaped agent. We demonstrate empirically the performance of reward shaping in two problem domains within the context of RoboCup KeepAway by designing three reward shaping schemes, encouraging specific behaviour such as keeping a minimum distance from other players on the same team and taking on specific roles. The results illustrate that reward shaping with multiple, simultaneous learning agents can reduce the time needed to learn a suitable policy and can alter the final group performance.

Keywords: Reinforcement learning; multi-agent; reward shaping (search for similar items in EconPapers)
Date: 2011
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0219525911002998
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:acsxxx:v:14:y:2011:i:02:n:s0219525911002998

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0219525911002998

Access Statistics for this article

Advances in Complex Systems (ACS) is currently edited by Frank Schweitzer

More articles in Advances in Complex Systems (ACS) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().