# Solving DCOPs with Distributed Large Neighborhood Search

## TL;DR

This paper introduces a Distributed Large Neighborhood Search framework for DCOPs that offers solution quality guarantees and leverages problem structure, outperforming existing incomplete algorithms in large-scale multi-agent optimization tasks.

## Contribution

The paper presents a novel D-LNS framework with a repair phase that guarantees solution quality and exploits problem structure, advancing incomplete DCOP solving methods.

## Key findings

- D-LNS outperforms existing incomplete algorithms on various problem instances.
- The framework provides bounds refinement during the iterative process.
- It effectively exploits domain-dependent knowledge and problem structure.

## Abstract

The field of Distributed Constraint Optimization has gained momentum in recent years, thanks to its ability to address various applications related to multi-agent cooperation. Nevertheless, solving Distributed Constraint Optimization Problems (DCOPs) optimally is NP-hard. Therefore, in large-scale, complex applications, incomplete DCOP algorithms are necessary. Current incomplete DCOP algorithms suffer of one or more of the following limitations: they (a) find local minima without providing quality guarantees; (b) provide loose quality assessment; or (c) are unable to benefit from the structure of the problem, such as domain-dependent knowledge and hard constraints. Therefore, capitalizing on strategies from the centralized constraint solving community, we propose a Distributed Large Neighborhood Search (D-LNS) framework to solve DCOPs. The proposed framework (with its novel repair phase) provides guarantees on solution quality, refining upper and lower bounds during the iterative process, and can exploit domain-dependent structures. Our experimental results show that D-LNS outperforms other incomplete DCOP algorithms on both structured and unstructured problem instances.