Opponent Modelling for Reinforcement Learning in Multi-Objective Normal Form Games: Extended Abstract

Yijie Zhang, Roxana Radulescu, Patrick Mannion, Diederik Roijers, Ann Nowe

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

16 Citations (Scopus)
177 Downloads (Pure)

Abstract

In this paper, we investigate the effects of opponent modelling on multi-objective multi-agent interactions with non-linear utilities. Specifically, we consider multi-objective normal form games (MONFGs) with non-linear utility functions under the scalarised expected returns optimisation criterion. We contribute a novel actor-critic formulation to allow reinforcement learning of mixed strategies in this setting, along with an extension that incorporates opponent policy reconstruction using conditional action frequencies. Our empirical results demonstrate that opponent modelling can drastically alter the learning dynamics in this setting.

Original languageEnglish
Title of host publicationProceedings of the 19th International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2020
EditorsBo An, Amal El Fallah Seghrouchni, Gita Sukthankar
PublisherIFAAMAS
Pages2080-2082
Number of pages3
ISBN (Electronic)978-1-4503-7518-4
Publication statusPublished - 2020
EventThe 19th International Conference on Autonomous Agents and Multi-Agent Systems - Auckland, New Zealand
Duration: 9 May 202013 May 2020
Conference number: 19
https://aamas2020.conference.auckland.ac.nz/
https://aamas2020.conference.auckland.ac.nz

Publication series

NameProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume2020-May
ISSN (Print)1548-8403
ISSN (Electronic)1558-2914

Conference

ConferenceThe 19th International Conference on Autonomous Agents and Multi-Agent Systems
Abbreviated titleAAMAS 2020
Country/TerritoryNew Zealand
CityAuckland
Period9/05/2013/05/20
Internet address

Fingerprint

Dive into the research topics of 'Opponent Modelling for Reinforcement Learning in Multi-Objective Normal Form Games: Extended Abstract'. Together they form a unique fingerprint.

Cite this