Graph Attention-based Grouped Multi-agent Reinforcement Learning Method

Currently,multi-agent reinforcement learning is widely applied in various cooperative tasks.In real environments,agents always have access to only partial observations,leading to inefficient exploration of cooperative strategies.Moreover,sharing reward values among agents makes it challenging to acc...

Cijeli opis

Bibliografski detalji

Glavni autor:	ZHU Shihao, PENG Kexing, MA Tinghuai
Format:	Artigo
Jezik:	Chinês
Izdano:	Editorial office of Computer Science 2025-09-01
Serija:	Jisuanji kexue
Teme:	multi-agent reinforcement learning|graph attention network|centralized training decentralized execution|multi-agent cooperation|multi-agent communication
Online pristup:	https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2025-52-9-330.pdf
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!