Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples

In this paper, we study the finite-time behavior of the TD(0) temporal-difference method with linear function approximation (LFA). We consider on-policy independent and identically distributed (i.i.d.) samples, a constant learning step, and the Polyak-Juditsky averaging method. We establish a new convergence rate, for the Mean-Square Error (MSE) on the approximated function, that is (i) fast in the sense that it admits an optimal dependency in the number of iterations k (i.e., of order 1/k), (ii) robust to ill-conditioning: it only depends on an initial error and modelindependent constants and (iii) sharp up to a multiplicative constant lower than 11. In particular, it does not depend on the smallest eigenvalue of the uncentered covariance matrix of the linear parametrization, unlike all pre-existing O(1/k) rates in the TD(0) literature. We also introduce PCTD(0), a variant of TD(0), which benefits from better convergence properties under an additional assumption of strong mixing on the Markov Chain.

On a Variance Reduction Correction of the Temporal Difference for Policy Evaluation in the Stochastic Continuous Setting

This paper deals with solving continuous time, state and action optimization problems in stochastic settings, using reinforcement learning algorithms, and considers the policy evaluation process. We prove that standard learning algorithms based on the discretized temporal difference are doomed to fail when the time discretization tends to zero, because of the stochastic part. We propose a variance-reduction correction of the temporal difference, leading to new learning algorithms that are stable with respect to vanishing time steps. This allows us to give theoretical guarantees of convergence of our algorithms to the solutions of continuous stochastic optimization problems.