United We Stand: Decentralized Multi-Agent Planning With Attrition
This addresses the challenge of agent attrition in cooperative multi-agent systems, which is critical for realistic large deployments but often poorly handled by current methods, representing an incremental advance with specific gains.
The paper tackles the problem of agent failures in decentralized multi-agent planning for information gathering tasks, proposing Attritable MCTS (A-MCTS) to enable timely and efficient adaptation, with results showing substantial improvements in global utility and scalability over existing approaches under high failure rates.
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.