By Shaan Haque and others

Stochastic approximation (SA) is an iterative algorithm to find the fixed point of an operator given noisy samples of this operator. SA appears in many areas such as optimization and Reinforcement Learning (RL). When implemented in practice, the noise that appears in the update of RL algorithms is naturally Markovian.... Show more

December 31, 2023

Loading full text...

Similar articles

Loading recommendations...

x1

Tight Finite Time Bounds of Two-Time-Scale Linear Stochastic Approximation with Markovian Noise

Click on play to start listening