Argumentation accelerated reinforcement learning for cooperative multi-agent systems. / Gao, Yang; Toni, Francesca.

ECAI'14 Proceedings of the Twenty-first European Conference on Artificial Intelligence. IOS Press, 2014. p. 333-338.

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

Published

Links

Abstract

Multi-Agent Learning is a complex problem, especially in real-time systems. We address this problem by introducing Argumentation Accelerated Reinforcement Learning (AARL), which provides a methodology for defining heuristics, represented by arguments, and incorporates these heuristics into Reinforcement Learning (RL) by using reward shaping. We define AARL via argumentation and prove that it can coordinate independent cooperative agents that have a shared goal but need to perform different actions. We test AARL empirically in a popular RL testbed, RoboCup Takeaway, and show that it significantly improves upon standard RL.
Original languageEnglish
Title of host publicationECAI'14 Proceedings of the Twenty-first European Conference on Artificial Intelligence
PublisherIOS Press
Pages333-338
Number of pages6
ISBN (Electronic)978-1-61499-418-3
DOIs
Publication statusPublished - 18 Aug 2014
This open access research output is licenced under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.

ID: 34316086