TY - GEN
T1 - Provably Efficient Algorithm for Nonstationary Low-Rank MDPs
AU - Cheng, Yuan
AU - Yang, Jing
AU - Liang, Yingbin
N1 - Publisher Copyright:
© 2023 Neural information processing systems foundation. All rights reserved.
PY - 2023
Y1 - 2023
N2 - 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 model contains unknown representation in addition to the linear state embedding function. We first propose a parameter-dependent policy optimization algorithm called PORTAL, and further improve PORTAL to its parameter-free version of Ada-PORTAL, which is able to tune its hyper-parameters adaptively without any prior knowledge of nonstationarity. For both algorithms, we provide upper bounds on the average dynamic suboptimality gap, which show that as long as the nonstationarity is not significantly large, PORTAL and Ada-PORTAL are sample-efficient and can achieve arbitrarily small average dynamic suboptimality gap with polynomial sample complexity.
AB - 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 model contains unknown representation in addition to the linear state embedding function. We first propose a parameter-dependent policy optimization algorithm called PORTAL, and further improve PORTAL to its parameter-free version of Ada-PORTAL, which is able to tune its hyper-parameters adaptively without any prior knowledge of nonstationarity. For both algorithms, we provide upper bounds on the average dynamic suboptimality gap, which show that as long as the nonstationarity is not significantly large, PORTAL and Ada-PORTAL are sample-efficient and can achieve arbitrarily small average dynamic suboptimality gap with polynomial sample complexity.
UR - https://www.scopus.com/pages/publications/85185570987
UR - https://www.scopus.com/pages/publications/85185570987#tab=citedBy
M3 - Conference contribution
AN - SCOPUS:85185570987
T3 - Advances in Neural Information Processing Systems
BT - Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023
A2 - Oh, A.
A2 - Neumann, T.
A2 - Globerson, A.
A2 - Saenko, K.
A2 - Hardt, M.
A2 - Levine, S.
PB - Neural information processing systems foundation
T2 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023
Y2 - 10 December 2023 through 16 December 2023
ER -