Model-Free Non-Stationary Reinforcement Learning: Near-Optimal Regret and Applications in Multi-Agent Reinforcement Learning and Inventory Control

Submitted by jiinkang@mit.edu on

TitleModel-Free Non-Stationary Reinforcement Learning: Near-Optimal Regret and Applications in Multi-Agent Reinforcement Learning and Inventory Control
Publication TypeJournal Article
Year of Publication2023
AuthorsMao W., Zhang K., Zhu R., Simchi-Levi D., Basar T.
JournalManagement Science

Type: 

Theory