Federico Berto, Chuanbo Hua, Laurin Luttmann, Jiwoo Son, Junyoung Park, Kyuree Ahn, Changhyun Kwon, Lin Xie, Jinkyoo Park
{"title":"PARCO:学习并行自回归政策,实现高效的多代理组合优化","authors":"Federico Berto, Chuanbo Hua, Laurin Luttmann, Jiwoo Son, Junyoung Park, Kyuree Ahn, Changhyun Kwon, Lin Xie, Jinkyoo Park","doi":"arxiv-2409.03811","DOIUrl":null,"url":null,"abstract":"Multi-agent combinatorial optimization problems such as routing and\nscheduling have great practical relevance but present challenges due to their\nNP-hard combinatorial nature, hard constraints on the number of possible\nagents, and hard-to-optimize objective functions. This paper introduces PARCO\n(Parallel AutoRegressive Combinatorial Optimization), a novel approach that\nlearns fast surrogate solvers for multi-agent combinatorial problems with\nreinforcement learning by employing parallel autoregressive decoding. We\npropose a model with a Multiple Pointer Mechanism to efficiently decode\nmultiple decisions simultaneously by different agents, enhanced by a\nPriority-based Conflict Handling scheme. Moreover, we design specialized\nCommunication Layers that enable effective agent collaboration, thus enriching\ndecision-making. We evaluate PARCO in representative multi-agent combinatorial\nproblems in routing and scheduling and demonstrate that our learned solvers\noffer competitive results against both classical and neural baselines in terms\nof both solution quality and speed. We make our code openly available at\nhttps://github.com/ai4co/parco.","PeriodicalId":501315,"journal":{"name":"arXiv - CS - Multiagent Systems","volume":"37 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"PARCO: Learning Parallel Autoregressive Policies for Efficient Multi-Agent Combinatorial Optimization\",\"authors\":\"Federico Berto, Chuanbo Hua, Laurin Luttmann, Jiwoo Son, Junyoung Park, Kyuree Ahn, Changhyun Kwon, Lin Xie, Jinkyoo Park\",\"doi\":\"arxiv-2409.03811\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Multi-agent combinatorial optimization problems such as routing and\\nscheduling have great practical relevance but present challenges due to their\\nNP-hard combinatorial nature, hard constraints on the number of possible\\nagents, and hard-to-optimize objective functions. This paper introduces PARCO\\n(Parallel AutoRegressive Combinatorial Optimization), a novel approach that\\nlearns fast surrogate solvers for multi-agent combinatorial problems with\\nreinforcement learning by employing parallel autoregressive decoding. We\\npropose a model with a Multiple Pointer Mechanism to efficiently decode\\nmultiple decisions simultaneously by different agents, enhanced by a\\nPriority-based Conflict Handling scheme. Moreover, we design specialized\\nCommunication Layers that enable effective agent collaboration, thus enriching\\ndecision-making. We evaluate PARCO in representative multi-agent combinatorial\\nproblems in routing and scheduling and demonstrate that our learned solvers\\noffer competitive results against both classical and neural baselines in terms\\nof both solution quality and speed. We make our code openly available at\\nhttps://github.com/ai4co/parco.\",\"PeriodicalId\":501315,\"journal\":{\"name\":\"arXiv - CS - Multiagent Systems\",\"volume\":\"37 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Multiagent Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.03811\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Multiagent Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.03811","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
PARCO: Learning Parallel Autoregressive Policies for Efficient Multi-Agent Combinatorial Optimization
Multi-agent combinatorial optimization problems such as routing and
scheduling have great practical relevance but present challenges due to their
NP-hard combinatorial nature, hard constraints on the number of possible
agents, and hard-to-optimize objective functions. This paper introduces PARCO
(Parallel AutoRegressive Combinatorial Optimization), a novel approach that
learns fast surrogate solvers for multi-agent combinatorial problems with
reinforcement learning by employing parallel autoregressive decoding. We
propose a model with a Multiple Pointer Mechanism to efficiently decode
multiple decisions simultaneously by different agents, enhanced by a
Priority-based Conflict Handling scheme. Moreover, we design specialized
Communication Layers that enable effective agent collaboration, thus enriching
decision-making. We evaluate PARCO in representative multi-agent combinatorial
problems in routing and scheduling and demonstrate that our learned solvers
offer competitive results against both classical and neural baselines in terms
of both solution quality and speed. We make our code openly available at
https://github.com/ai4co/parco.