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 language | English |
---|---|
Title of host publication | Proceedings of the 19th International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2020 |
Editors | Bo An, Amal El Fallah Seghrouchni, Gita Sukthankar |
Publisher | IFAAMAS |
Pages | 2080-2082 |
Number of pages | 3 |
ISBN (Electronic) | 978-1-4503-7518-4 |
Publication status | Published - 2020 |
Event | The 19th International Conference on Autonomous Agents and Multi-Agent Systems - Auckland, New Zealand Duration: 9 May 2020 → 13 May 2020 Conference number: 19 https://aamas2020.conference.auckland.ac.nz/ https://aamas2020.conference.auckland.ac.nz |
Publication series
Name | Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS |
---|---|
Volume | 2020-May |
ISSN (Print) | 1548-8403 |
ISSN (Electronic) | 1558-2914 |
Conference
Conference | The 19th International Conference on Autonomous Agents and Multi-Agent Systems |
---|---|
Abbreviated title | AAMAS 2020 |
Country/Territory | New Zealand |
City | Auckland |
Period | 9/05/20 → 13/05/20 |
Internet address |