On Supervised Online Rolling-Horizon Control for Infinite-Horizon Discounted Markov Decision Processes

• 成果类型: Article
• 署名作者: Chang, Hyeong Soo
• 署名单位: Sogang University
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2023.3274791
• 发表日期: 2024
• 页码: 1060-1065
• 关键词: Markov processes; Heuristic algorithms; Markov decision process (MDP); policy iteration (PI); policy switching; rolling horizon control

摘要

This note revisits the rolling-horizon control approach to the problem of Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished from the classical value-iteration approaches, we develop an asynchronous online algorithm based on policy iteration integrated with a multipolicy improvement method of policy switching. A sequence of monotonically improving solutions to the forecast-horizon sub-MDP is generated by updating the current solution only at the currently visited state, building in effect a rolling-horizon control policy for the MDP over infinite horizon. Feedbacks from supervisors, if available, can be also incorporated while updating. We focus on the convergence issue with a relation to the transition structure of the MDP. Either a global convergence to an optimal forecast-horizon policy or a local convergence to a locally-optimal fixed-policy in a finite time is achieved by the algorithm depending on the structure.