Multi-agent active perception with prediction rewards

TL;DR

This paper models multi-agent active perception as a Dec-POMDP with prediction rewards, providing theoretical bounds and practical algorithms to improve scalability and planning in decentralized observation tasks.

Contribution

It introduces a novel Dec-POMDP formulation with individual prediction actions, bounding decentralization loss and enabling application of existing algorithms to active perception.

Findings

Bounded loss due to decentralization

Application of Dec-POMDP algorithms improves scalability

Empirical results show enhanced planning efficiency

Abstract

Multi-agent active perception is a task where a team of agents cooperatively gathers observations to compute a joint estimate of a hidden variable. The task is decentralized and the joint estimate can only be computed after the task ends by fusing observations of all agents. The objective is to maximize the accuracy of the estimate. The accuracy is quantified by a centralized prediction reward determined by a centralized decision-maker who perceives the observations gathered by all agents after the task ends. In this paper, we model multi-agent active perception as a decentralized partially observable Markov decision process (Dec-POMDP) with a convex centralized prediction reward. We prove that by introducing individual prediction actions for each agent, the problem is converted into a standard Dec-POMDP with a decentralized prediction reward. The loss due to decentralization is bounded, and we give a sufficient condition for when it is zero. Our results allow application of any Dec-POMDP solution algorithm to multi-agent active perception problems, and enable planning to reduce uncertainty without explicit computation of joint estimates. We demonstrate the empirical usefulness of our results by applying a standard Dec-POMDP algorithm to multi-agent active perception problems, showing increased scalability in the planning horizon.