The Curious Case of Exploding DecPOMDPs: Containing the Fire through Policy Counting

2026-08-18

AI Summary

该论文针对DecPOMDP中因代理数量增加导致的复杂度爆炸问题，提出了一种通过计数策略而非代理来简化模型的方法，并使用动态规划有效求解。

Abstract

Decentralised partially observable Markov decision processes (DecPOMDPs) provide a general framework for modelling multi-agent decision making under uncertainty. However, DecPOMDPs are known to suffer from exponential complexity in the number of agents. One way to combat this intractability in agent numbers is to look at partitions of agents that exhibit a form of symmetry among agents, allowing for a compact encoding by counting. However, a challenge arises as the policy space explodes, even though the model complexity and evaluation cost reduce to a polynomial dependence. In this paper, we redirect our focus from counting agents to counting policies, which actually enables tractability in agent numbers for so called policy-counted DecPOMDPs. Further, we present policy-counted dynamic programming using the compact representation to solve policy-counted DecPOMDPs efficiently.

Problem

• DecPOMDPs
• multi-agent decision making
• exponential complexity
• policy space explosion
• symmetry

Innovation

• policy counting
• DecPOMDPs
• dynamic programming