@inproceedings{6a5e3bec2ea741ad81876030157a6d7a,
title = "Disentangling Successor Features for Coordination in Multi-agent Reinforcement Learning",
abstract = "Multi-agent reinforcement learning (MARL) is a promising framework for solving complex tasks with many agents. However, a key challenge in MARL is defining private utility functions that ensure coordination when training decentralized agents. This challenge is especially prevalent in unstructured tasks with sparse rewards and many agents. We show that successor features can help address this challenge by disentangling an individual agent's impact on the global value function from that of all other agents. We use this disentanglement to compactly represent private utilities that support stable training of decentralized agents in unstructured tasks. We implement our approach using a centralized training, decentralized execution architecture and test it in a variety of multi-agent environments. Our results show improved performance and training time relative to existing methods and suggest that disentanglement of successor features offers a promising approach to coordination in MARL.",
keywords = "Coordination, Multi-Agent Reinforcement Learning, Reinforcement Learning",
author = "Kim, {Seung Hyun} and {Van Stralen}, Neale and Girish Chowdhary and Tran, {Huy T.}",
note = "Publisher Copyright: {\textcopyright} 2022 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved; 21st International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022 ; Conference date: 09-05-2022 Through 13-05-2022",
year = "2022",
language = "English (US)",
series = "Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS",
publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",
pages = "751--760",
booktitle = "International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022",
}