No Panacea in Planning: Algorithm Selection for Suboptimal Multi-Agent Path Finding

Weizhe Chen, Zhihan Wang,Jiaoyang Li,Sven Koenig,Bistra Dilkina

Computing Research Repository (CoRR)（2024）

University of Southern | The University of Texas at Austin | Carnegie Mellon University

Cited 0|Views33

Abstract

Since more and more algorithms are proposed for multi-agent path finding(MAPF) and each of them has its strengths, choosing the correct one for aspecific scenario that fulfills some specified requirements is an importanttask. Previous research in algorithm selection for MAPF built a standardworkflow and showed that machine learning can help. In this paper, we studygeneral solvers for MAPF, which further include suboptimal algorithms. Wepropose different groups of optimization objectives and learning tasks tohandle the new tradeoff between runtime and solution quality. We conductextensive experiments to show that the same loss can not be used for differentgroups of optimization objectives, and that standard computer vision models areno worse than customized architecture. We also provide insightful discussionson how feature-sensitive pre-processing is needed for learning for MAPF, andhow different learning metrics are correlated to different learning tasks.

Translated text

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Try using models to generate summary,it takes about 60s

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper