MODEL-FREE MEAN-FIELD REINFORCEMENT LEARNING: MEAN-FIELD MDP AND MEAN-FIELD Q-LEARNING

Carmona, R; Laurière, M; Tan, ZJ

Carmona, R (通讯作者),Princeton Univ, Dept Operat Res & Financial Engn, Princeton, NJ 08544 USA.

ANNALS OF APPLIED PROBABILITY, 2023; 33 (6B): 5334

Abstract

We study infinite horizon discounted mean field control (MFC) prob-lems with common noise through the lens of mean field Markov decision processes (MF......

Full Text Link