By the same authors

Theoretical Considerations of Potential-Based Reward Shaping for Multi-Agent Systems

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

Full text download(s)

Links

Author(s)

Department/unit(s)

Publication details

Title of host publicationThe 10th International Conference on Autonomous Agents and Multiagent Systems
DatePublished - May 2011
Pages225-232
PublisherACM
Original languageEnglish
ISBN (Electronic)0-9826571-5-3
ISBN (Print)978-0-9826571-5-7

Abstract

Potential-based reward shaping has previously been proven
to both be equivalent to Q-table initialisation and guarantee
policy invariance in single-agent reinforcement learning.
The method has since been used in multi-agent reinforcement
learning without consideration of whether the theoretical
equivalence and guarantees hold. This paper extends
the existing proofs to similar results in multi-agent systems,
providing the theoretical background to explain the success
of previous empirical studies. Specically, it is proven
that the equivalence to Q-table initialisation remains and
the Nash Equilibria of the underlying stochastic game are
not modied. Furthermore, we demonstrate empirically that
potential-based reward shaping eects exploration and,
consequentially, can alter the joint policy converged upon.

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations