Primal-Dual Representation Learning for Low-Rank Constrained MDPs
Representation learning has substantially improved the efficiency of unconstrained continuous-state Markov Decision Processes (MDPs), but its extension to Constrained MDPs (CMDPs) is difficult because the transition representation must be learned while constraint violation is controlled. In this paper, we study represe...
Chen-Hao Zhou, Chao Zhang, Wen-Song Bai et al.
· 0 citations