Reinforcement Learning for Stochastic Networks, Toulouse

Session

Keynote: Éric Moulines (École Polytechnique)

Jun 18, 2024, 9:30 AM

Amphi B00 (ENSEEIHT)

88. Finite Sample analysis of linear stochastic approximation and TD learning

6/18/24, 9:30 AM

Abstract: In this talk, we consider the problem of obtaining sharp bounds for linear stochastic approximation. We then apply these results to temporal difference (TD) methods with linear functional approximation for policy evaluation in discounted Markov decision processes. We show that a simple algorithm with a universal and instance-independent step size together with Polyak-Ruppert tail...