Regret-Based Multi-Agent Coordination with Uncertain Task Rewards
원문 초록
Many multi-agent coordination problems can be represented as DCOPs. Motivated by task allocation in disaster response, we extend standard DCOP models to consider uncertain task rewards where the outcome of completing a task depends on its current state, which is randomly drawn from unknown distributions. The goal of solving this problem is to find a solution for all agents that minimizes the overall worst-case loss. This is a challenging problem for centralized algorithms because the search space grows exponentially with the number of agents and is nontrivial for standard DCOP algorithms we have. To address this, we propose a novel decentralized algorithm that incorporates Max-Sum with iterative constraint generation to solve the problem by passing messages among agents. By so doing, our approach scales well and can solve instances of the task allocation problem with hundreds of agents and tasks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Differential Attention for Multimodal Crisis Event Analysis
Cloud-Aware SAR Fusion for Enhanced Optical Sensing in Space Missions
GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models
VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and Beyond
REOBench: Benchmarking Robustness of Earth Observation Foundation Models
FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.