Multiagent Reinforcement Learning:Rollout and Policy IterationOACSCD

作者：Dimitri Bertsekas

作者单位：Arizona State University (ASU), Tempe, AZ 85281 USA, and also with Massachusetts Institute of Technology (MIT), Cambridge, MA 02139 USA

中文关键词：Dynamic programmingmultiagent problemsneuro-dynamic programmingpolicy iterationreinforcement learningrollout

英文关键词：Dynamic programmingmultiagent problemsneuro-dynamic programmingpolicy iterationreinforcement learningrollout

刊名：《自动化学报（英文版）》 2021 (2)

页码/页数：249-272,24

DOI：10.1109/JAS.2021.1003814