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 docs 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.
|Title of host publication||36th International Conference on Machine Learning, ICML 2019|
|Publisher||International Machine Learning Society (IMLS)|
|Number of pages||18|
|Publication status||Published - 2019|
|Event||36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States|
Duration: 2019 Jun 9 → 2019 Jun 15
|Name||36th International Conference on Machine Learning, ICML 2019|
|Conference||36th International Conference on Machine Learning, ICML 2019|
|Period||19/6/9 → 19/6/15|
Bibliographical notePublisher Copyright:
© 2019 International Machine Learning Society (IMLS).
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Human-Computer Interaction