Print Email Facebook Twitter The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning Title The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning Author Castellini, Jacopo (University of Liverpool) Oliehoek, F.A. (TU Delft Interactive Intelligence) Savani, Rahul (University of Liverpool) Whiteson, Shimon (University of Oxford) Date 2019 Abstract Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. In this work, we empirically investigate the representational power of various network architectures on a series of one-shot games. Despite their simplicity, these games capture many of the crucial problems that arise in the multi-agent setting, such as an exponential number of joint actions or the lack of an explicit coordination mechanism. Our results quantify how well various approaches can represent the requisite value functions, and help us identify issues that can impede good performance. Subject Actionvalue representationDecision-makingMulti-agent systemsNeural networksOne-shot games To reference this document use: http://resolver.tudelft.nl/uuid:8ca4ef09-6fc8-47de-b2c9-bc33671854ca Publisher International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) Embargo date 2019-11-08 ISBN 978-1-4503-6309-9 Source 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019: Proceedings of the Eighteenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS) Event AAMAS 2019, 2019-05-13 → 2019-05-17, Montreal, Canada Series Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, 1548-8403, 4 Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2019 Jacopo Castellini, F.A. Oliehoek, Rahul Savani, Shimon Whiteson Files PDF TRC.pdf 1.21 MB Close viewer /islandora/object/uuid:8ca4ef09-6fc8-47de-b2c9-bc33671854ca/datastream/OBJ/view