By the same authors

From the same journal

Plan-based reward shaping for multi-agent reinforcement learning

Research output: Contribution to journalArticle

Published copy (DOI)

Author(s)

Department/unit(s)

Publication details

JournalThe Knowledge Engineering Review
DatePublished - 11 Feb 2016
Issue number1
Volume31
Number of pages15
Pages (from-to)44-58
Original languageEnglish

Abstract

Recent theoretical results have justified the use of potential-based reward shaping as a way to improve the performance of multi-agent reinforcement learning (MARL). However, the question remains of how to generate a useful potential function. Previous research demonstrated the use of STRIPS operator knowledge to automatically generate a potential function for single-agent reinforcement learning. Following up on this work, we investigate the use of STRIPS planning knowledge in the context of MARL. Our results show that a potential function based on joint or individual plan knowledge can significantly improve MARL performance compared with no shaping. In addition, we investigate the limitations of individual plan knowledge as a source of reward shaping in cases where the combination of individual agent plans causes conflict.

Discover related content

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

View graph of relations