QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning

Autor:	Son, Kyunghwan, Kim, Daewoo, Kang, Wan Ju, Hostallero, David Earl, Yi, Yung
Rok vydání:	2019
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Multiagent Systems Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	We explore value-based solutions for multi-agent reinforcement learning (MARL) tasks in the centralized training with decentralized execution (CTDE) regime popularized recently. However, VDN and QMIX are representative examples that use the idea of factorization of the joint action-value function into individual ones for decentralized execution. VDN and QMIX address only a fraction of factorizable MARL tasks due to their structural constraint in factorization such as additivity and monotonicity. In this paper, we propose a new factorization method for MARL, QTRAN, which is free from such structural constraints and takes on a new approach to transforming the original joint action-value function into an easily factorizable one, with the same optimal actions. QTRAN guarantees more general factorization than VDN or QMIX, thus covering a much wider class of MARL tasks than does previous methods. Our experiments for the tasks of multi-domain Gaussian-squeeze and modified predator-prey demonstrate QTRAN's superior performance with especially larger margins in games whose payoffs penalize non-cooperative behavior more aggressively. Comment: 18 pages; Accepted to ICML 2019
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1905.05408 Zobrazit plný text záznamu View this record from Arxiv