# Planning for Decentralized Control of Multiple Robots Under Uncertainty

arXiv: https://arxiv.org/abs/1402.2871 · HTML: https://mlsanity.com/paper/1402.2871/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2014.

## Built on by (most cited first, 7 of 7)

- [Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2209.10113/) (2022)
- [From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents](https://mlsanity.com/paper/2602.04326/) (2026)
- [Macro-Action-Based Multi-Agent/Robot Deep Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/2209.10003/) (2022)
- [Distributed Online Rollout for Multivehicle Routing in Unmapped Environments](https://mlsanity.com/paper/2305.15596/) (2023)
- [HARMONIC: Cognitive and Control Collaboration in Human-Robotic Teams](https://mlsanity.com/paper/2409.18047/) (2024)
- [Formal Modelling for Multi-Robot Systems Under Uncertainty](https://mlsanity.com/paper/2305.17018/) (2023)
- [Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.12655/) (2026)

## Abstract (arXiv)

We describe a probabilistic framework for synthesizing control policies for general multi-robot systems, given environment and sensor models and a cost function. Decentralized, partially observable Markov decision processes (Dec-POMDPs) are a general model of decision processes where a team of agents must cooperate to optimize some objective (specified by a shared reward or cost function) in the presence of uncertainty, but where communication limitations mean that the agents cannot share their state, so execution must proceed in a decentralized fashion. While Dec-POMDPs are typically intractable to solve for real-world problems, recent research on the use of macro-actions in Dec-POMDPs has significantly increased the size of problem that can be practically solved as a Dec-POMDP. We describe this general model, and show how, in contrast to most existing methods that are specialized to a particular problem class, it can synthesize control policies that use whatever opportunities for coordination are present in the problem, while balancing off uncertainty in outcomes, sensor information, and information about other agents. We use three variations on a warehouse task to show that a single planner of this type can generate cooperative behavior using task allocation, direct communication, and signaling, as appropriate.