# Towards Optimal Performance and Action Consistency Guarantees in Dec-POMDPs with Inconsistent Beliefs and Limited Communication

arXiv: https://arxiv.org/abs/2512.20778 · HTML: https://mlsanity.com/paper/2512.20778/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Builds on (most cited first, 9 of 9)

- [Stochastic Dynamic Games in Belief Space](https://mlsanity.com/paper/1909.06963/) (2019)
- [Scalable Planning and Learning for Multiagent POMDPs: Extended Version](https://mlsanity.com/paper/1404.1140/) (2014)
- [Simplified decision making in the belief space using belief sparsification](https://mlsanity.com/paper/1909.00885/) (2019)
- [Nonmyopic Distilled Data Association Belief Space Planning Under Budget Constraints](https://mlsanity.com/paper/2207.08096/) (2022)
- [MPOGames: Efficient Multimodal Partially Observable Dynamic Games](https://mlsanity.com/paper/2210.10814/) (2022)
- [Bridging the Gap between Partially Observable Stochastic Games and Sparse POMDP Methods](https://mlsanity.com/paper/2405.18703/) (2024)
- [Monte Carlo Planning in Hybrid Belief POMDPs](https://mlsanity.com/paper/2211.07735/) (2022)
- [Simplifying Complex Observation Models in Continuous POMDP Planning with Probabilistic Guarantees and Practice](https://mlsanity.com/paper/2311.07745/) (2023)
- [Action-Consistent Decentralized Belief Space Planning with Inconsistent Beliefs and Limited Data Sharing: Framework and Simplification Algorithms with Formal Guarantees](https://mlsanity.com/paper/2403.05962/) (2024)

## Abstract (arXiv)

Multi-agent decision-making under uncertainty is fundamental for effective and safe autonomous operation. In many real-world scenarios, each agent maintains its own belief over the environment and must plan actions accordingly. However, most existing approaches assume that all agents have identical beliefs at planning time, implying these beliefs are conditioned on the same data. Such an assumption is often impractical due to limited communication. In reality, agents frequently operate with inconsistent beliefs, which can lead to poor coordination and suboptimal, potentially unsafe, performance. In this paper, we address this critical challenge by introducing a novel decentralized framework for optimal joint action selection that explicitly accounts for belief inconsistencies. Our approach provides probabilistic guarantees for both action consistency and performance with respect to open-loop multi-agent POMDP (which assumes all data is always communicated), and selectively triggers communication only when needed. Furthermore, we address another key aspect of whether, given a chosen joint action, the agents should share data to improve expected performance in inference. Simulation results show our approach outperforms state-of-the-art algorithms.