首页|Perception field based imitation learning for unlabeled multi-agent pathfinding

Perception field based imitation learning for unlabeled multi-agent pathfinding

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
This paper proposes an imitation learning method to learn a universal agent policy for unlabeled multi-agent pathfinding(unlabeled MAPF)in grid environments.The method transforms the unlabeled MAPF problem into a series of temporal-independent homogeneous classification problems for each agent.Based on this transformation,a neural network is designed to imitate a distance-optimal expert algorithm.The neural network consists of two successive modules:perception field learner and field integrating classifier.The former refines and encodes the current system state into a perception field for each agent by combining a set of learnable field-generating functions.The latter takes an agent's perception field as input and decides the agent's next action based on a triplet cross-attention mechanism.We evaluate our method on a diverse set of unlabeled MAPF tasks.Compared with state-of-the-art counterparts,the experimental results manifest the superiority of the proposed method in both generalization ability and scalability.

unlabeled multi-agent pathfindingperception fieldtriplet cross-attentionmulti-agent imita-tion learninglearning-based planning

Wenjie CHU、Ailun YU、Wei ZHANG、Haiyan ZHAO、Zhi JIN

展开 >

School of Computer Science,Peking University,Beijing 100871,China

Key Laboratory of High-Confidence Software Technologies(Peking University),Ministry of Education,Beijing 100871,China

National Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaNational Natural Science Foundation of China

621927316219273062190200

2024

10.1007/s11432-022-3666-2

中国科学:信息科学(英文版)
中国科学院

中国科学:信息科学(英文版)

CSTPCDEI
影响因子：0.715
ISSN：1674-733X
年,卷(期)：2024.67(5)
  • 48