Solving Collaborative Dec-POMDPs with Deep Reinforcement Learning Heuristics
Not on the map. Why?
Abstract (arXiv)
WQMIX, QMIX, QTRAN, and VDN are SOTA algorithms for Dec-POMDP. All of them cannot solve complex agents' cooperation domains. We give an algorithm to solve such problems. In the first stage, we solve a single-agent problem and get a policy. In the second stage, we solve the multi-agent problem with the single-agent policy. SA2MA has a clear advantage over all competitors in complex agents' cooperative domains.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 7 of its 16 references that are in the map. First posted on arXiv 9 Nov 2022.
Builds on
7 of 16 references.
References · 7
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 490
- 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 372
- 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
- 2020Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 197
- 2017Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Playcited by 139
- 2018CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learningcited by 31
Built on by
Not cited yet.