Provably Efficient Algorithm for Nonstationary Low-Rank MDPs. (arXiv:2308.05471v1 [cs.LG])

Reinforcement learning (RL) under changing environment models many real-world
applications via nonstationary Markov Decision Processes (MDPs), and hence
gains considerable interest. However, theoretical studies on nonstationary MDPs
in the literature have mainly focused on tabular and linear (mixture) MDPs,
which do not capture the nature of unknown representation in deep RL. In this
paper, we make the first effort to investigate nonstationary RL under episodic
low-rank MDPs, where both transition kernels and rewards may vary over time,
and the low-rank …

algorithm applications arxiv decision deep rl environment linear literature low markov nature processes reinforcement reinforcement learning representation studies tabular world