Keywords: TDC, finite-sample analysis, tracking error bound, Markovian noise, non-convex
TL;DR: This paper provides a non-asymptotic analysis for the TDC algorithm with general smooth function approximation.
Abstract: Temporal-difference learning with gradient correction (TDC) is a two time-scale algorithm for policy evaluation in reinforcement learning. This algorithm was initially proposed with linear function approximation, and was later extended to the one with general smooth function approximation. The asymptotic convergence for the on-policy setting with general smooth function approximation was established in [Bhatnagar et al., 2009], however, the non-asymptotic convergence analysis remains unsolved due to challenges in the non-linear and two-time-scale update structure, non-convex objective function and the projection onto a time-varying tangent plane. In this paper, we develop novel techniques to address the above challenges and explicitly characterize the non-asymptotic error bound for the general off-policy setting with i.i.d. or Markovian samples, and show that it converges as fast as $\mathcal O(1/\sqrt T)$ (up to a factor of $\mathcal O(\log T)$). Our approach can be applied to a wide range of value-based reinforcement learning algorithms with general smooth function approximation.
Supplementary Material: pdf
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.