English

Concentration of Contractive Stochastic Approximation and Reinforcement Learning

Machine Learning 2022-06-14 v4 Systems and Control Systems and Control

Abstract

Using a martingale concentration inequality, concentration bounds `from time n0n_0 on' are derived for stochastic approximation algorithms with contractive maps and both martingale difference and Markov noises. These are applied to reinforcement learning algorithms, in particular to asynchronous Q-learning and TD(0).

Keywords

Cite

@article{arxiv.2106.14308,
  title  = {Concentration of Contractive Stochastic Approximation and Reinforcement Learning},
  author = {Siddharth Chandak and Vivek S. Borkar and Parth Dodhia},
  journal= {arXiv preprint arXiv:2106.14308},
  year   = {2022}
}

Comments

20 pages, Accepted for publication in Stochastic Systems

R2 v1 2026-06-24T03:38:44.336Z