United We Stand: Decentralized Multi-Agent Planning With Attrition

TL;DR

This paper introduces Attritable MCTS, a decentralized multi-agent planning algorithm that adapts efficiently to agent failures, significantly improving performance and scalability in information gathering tasks.

Contribution

The paper presents A-MCTS, a novel decentralized MCTS algorithm that effectively handles agent failures using global reward estimation and regret matching for coordination.

Findings

A-MCTS adapts efficiently under high failure rates.

It outperforms existing approaches in global utility.

It demonstrates scalability in large, failure-prone scenarios.

Abstract

Decentralized planning is a key element of cooperative multi-agent systems for information gathering tasks. However, despite the high frequency of agent failures in realistic large deployment scenarios, current approaches perform poorly in the presence of failures, by not converging at all, and/or by making very inefficient use of resources (e.g. energy). In this work, we propose Attritable MCTS (A-MCTS), a decentralized MCTS algorithm capable of timely and efficient adaptation to changes in the set of active agents. It is based on the use of a global reward function for the estimation of each agent's local contribution, and regret matching for coordination. We evaluate its effectiveness in realistic data-harvesting problems under different scenarios. We show both theoretically and experimentally that A-MCTS enables efficient adaptation even under high failure rates. Results suggest that, in the presence of frequent failures, our solution improves substantially over the best existing approaches in terms of global utility and scalability.