A Decentralized Partially Observable Team Decision Methodology with Delayed Information Sharing

2026-09-22

AI Summary

研究通过结合团队理论等价与低秩模型表示，解决了部分可观测且系统模型未知的团队决策问题，提出了一种基于延迟信息共享的去中心化学习和规划算法。

Abstract

We study decentralized partially observable team decision problems with low-rank latent dynamics and unknown system models. The proposed framework combines team-theoretic equivalence with low-rank model representations to address cooperative decision-making in partially observable Markov decision processes without prior knowledge of the transition model. Each team member makes decisions based on local private information and delayed common information shared across the team. Using only this available information, each member learns an approximate low-rank Markov decision process and applies least-squares value iteration to compute its policy. This yields a fully decentralized learning and planning algorithm that requires neither a centralized coordinator nor centralized training. We show that the resulting member-side solutions approximate the centralized team solution: despite partial observability, unknown dynamics, and delayed common information, each member recovers the corresponding component of an approximate team-optimal policy. We further establish finite-sample performance guarantees and derive a corresponding sample-complexity bound for the proposed algorithm.

Problem

• decentralized
• partially observable
• team decision
• delayed information sharing
• unknown system models

Innovation

• Decentralized Learning
• Low-rank Model
• Partially Observable Markov Decision Processes
• Delayed Information Sharing