PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Berto, Federico, Hua, Chuanbo, Luttmann, Laurin, Son, Jiwoo, Park, Junyoung, Ahn, Kyuree, Kwon, Changhyun, Xie, Lin, Park, Jinkyoo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917030871957504
author Berto, Federico
Hua, Chuanbo
Luttmann, Laurin
Son, Jiwoo
Park, Junyoung
Ahn, Kyuree
Kwon, Changhyun
Xie, Lin
Park, Jinkyoo
author_facet Berto, Federico
Hua, Chuanbo
Luttmann, Laurin
Son, Jiwoo
Park, Junyoung
Ahn, Kyuree
Kwon, Changhyun
Xie, Lin
Park, Jinkyoo
contents Combinatorial optimization problems involving multiple agents are notoriously challenging due to their NP-hard nature and the necessity for effective agent coordination. Despite advancements in learning-based methods, existing approaches often face critical limitations, including suboptimal agent coordination, poor generalization, and high computational latency. To address these issues, we propose PARCO (Parallel AutoRegressive Combinatorial Optimization), a general reinforcement learning framework designed to construct high-quality solutions for multi-agent combinatorial tasks efficiently. To this end, PARCO integrates three key novel components: (1) transformer-based communication layers to enable effective agent collaboration during parallel solution construction, (2) a multiple pointer mechanism for low-latency, parallel agent decision-making, and (3) priority-based conflict handlers to resolve decision conflicts via learned priorities. We evaluate PARCO in multi-agent vehicle routing and scheduling problems, where our approach outperforms state-of-the-art learning methods, demonstrating strong generalization ability and remarkable computational efficiency. We make our source code publicly available to foster future research: https://github.com/ai4co/parco.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03811
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization
Berto, Federico
Hua, Chuanbo
Luttmann, Laurin
Son, Jiwoo
Park, Junyoung
Ahn, Kyuree
Kwon, Changhyun
Xie, Lin
Park, Jinkyoo
Multiagent Systems
Artificial Intelligence
Combinatorial optimization problems involving multiple agents are notoriously challenging due to their NP-hard nature and the necessity for effective agent coordination. Despite advancements in learning-based methods, existing approaches often face critical limitations, including suboptimal agent coordination, poor generalization, and high computational latency. To address these issues, we propose PARCO (Parallel AutoRegressive Combinatorial Optimization), a general reinforcement learning framework designed to construct high-quality solutions for multi-agent combinatorial tasks efficiently. To this end, PARCO integrates three key novel components: (1) transformer-based communication layers to enable effective agent collaboration during parallel solution construction, (2) a multiple pointer mechanism for low-latency, parallel agent decision-making, and (3) priority-based conflict handlers to resolve decision conflicts via learned priorities. We evaluate PARCO in multi-agent vehicle routing and scheduling problems, where our approach outperforms state-of-the-art learning methods, demonstrating strong generalization ability and remarkable computational efficiency. We make our source code publicly available to foster future research: https://github.com/ai4co/parco.
title PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization
topic Multiagent Systems
Artificial Intelligence
url https://arxiv.org/abs/2409.03811