ET-HF: A novel information sharing model to improve multi-agent cooperation

作者：

Highlights：

• A novel model is proposed to solve partial observability and improve cooperation.

• A topology-sharing scheme is proposed to make messages contain more features.

• The effectiveness of the proposed model is validated in swarm robotic benchmark tasks.

摘要

•A novel model is proposed to solve partial observability and improve cooperation.•A topology-sharing scheme is proposed to make messages contain more features.•The effectiveness of the proposed model is validated in swarm robotic benchmark tasks.

论文关键词：Multi-agent reinforcement learning,Multi-agent cooperation,Communication,Graph neural network

论文评审过程：Received 1 August 2022, Revised 14 September 2022, Accepted 15 September 2022, Available online 22 September 2022, Version of Record 17 October 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109916