Print Email Facebook Twitter Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning Title Analysing factorizations of action-value networks for cooperative 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 2021 Abstract Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are learning, or how we should enhance their learning power to address the problems on which they fail. In this work, we empirically investigate the learning 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 extend those in Castellini et al. (Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS’19.International Foundation for Autonomous Agents and Multiagent Systems, pp 1862–1864, 2019) and quantify how well various approaches can represent the requisite value functions, and help us identify the reasons that can impede good performance, like sparsity of the values or too tight coordination requirements. Subject Action-value representationDecision-makingMulti-agent systemsNeural networksOne-shot games To reference this document use: http://resolver.tudelft.nl/uuid:49288083-b5f9-431f-8371-47dc4b789134 DOI https://doi.org/10.1007/s10458-021-09506-w ISSN 1387-2532 Source Autonomous Agents and Multi-Agent Systems, 35 (2), 1-53 Part of collection Institutional Repository Document type journal article Rights © 2021 Jacopo Castellini, F.A. Oliehoek, Rahul Savani, Shimon Whiteson Files PDF Castellini2021_Article_An ... fActio.pdf 3.32 MB Close viewer /islandora/object/uuid:49288083-b5f9-431f-8371-47dc4b789134/datastream/OBJ/view