A Semi-Decentralized Approach to Multiagent Control
Not on the map. Why?
Abstract (arXiv)
We introduce an expressive framework and algorithms for the semi-decentralized control of cooperative agents in environments with communication uncertainty. Whereas semi-Markov control admits a distribution over time for agent actions, semi-Markov communication, or what we refer to as semi-decentralization, gives a distribution over time for what actions and observations agents can store in their histories. We extend semi-decentralization to the partially observable Markov decision process (POMDP). The resulting SDec-POMDP unifies decentralized and multiagent POMDPs and several existing explicit communication mechanisms. We present recursive small-step semi-decentralized A* (RS-SDA*), an exact algorithm for generating optimal SDec-POMDP policies. RS-SDA* is evaluated on semi-decentralized versions of several standard benchmarks and a maritime medical evacuation scenario. This paper provides a well-defined theoretical foundation for exploring many classes of multiagent communication problems through the lens of semi-decentralization.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 6 of its 33 references that are in the map. First posted on arXiv 12 Mar 2026.
Builds on
6 of 33 references.
References · 6
- 2013The Complexity of Decentralized Control of Markov Decision Processescited by 225
- 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 170
- 2018Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Taskscited by 114
- 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 103
- 2018Distributed Wildfire Surveillance with Autonomous Aircraft using Deep Reinforcement Learningcited by 16
- 2020A Unifying Framework for Reinforcement Learning and Planningcited by 4
Built on by
Not cited yet.