On $\mathcal{O}(1/K)$ Convergence and Low Sample Complexity for Single-Timescale Policy Evaluation with Nonlinear Function Approximation

Zhuqing Liu, Xin Zhang, Jia Liu, Zhengyuan Zhu, Songtao Lu

Abstract: Learning an accurate value function for a given policy is a critical step in solving reinforcement learning (RL) problems. So far, however, the convergence speed and sample complexity performances of most existing policy evaluation algorithms remain unsatisfactory, particularly with {\em non-linear} function approximation. This challenge motivates us to develop a new variance-reduced primal-dual method (VRPD) that is able to achieve a fast convergence speed for RL policy evaluation with nonlinear function approximation. To lower the high sample complexity limitation of variance-reduced approaches (due to the periodic full gradient evaluation with all training data), we further propose an enhanced VRPD method with an adaptive-batch adjustment (VRPD$^+$). The main features of VRPD include: i) VRPD allows the use of {\em{constant}} step sizes and achieves the $\mathcal{O}(1/K)$ convergence rate to the first-order stationary points of non-convex policy evaluation problems; ii) VRPD is a generic {\em{single}}-timescale algorithm that is also applicable for solving a large class of non-convex strongly-concave minimax optimization problems; iii) By adaptively adjusting the batch size via historical stochastic gradient information, VRPD$^+$ is more sample-efficient in practice without loss of theoretical convergence rate. Our extensive numerical experiments verify our theoretical findings and showcase the high efficiency of the proposed VRPD and VRPD$^+$ algorithms compared with the state-of-the-art methods.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Optimization (eg, convex and non-convex optimization)