English

Concentration bounds for SSP Q-learning for average cost MDPs

Machine Learning 2022-06-14 v2 Optimization and Control Machine Learning

Abstract

We derive a concentration bound for a Q-learning algorithm for average cost Markov decision processes based on an equivalent shortest path problem, and compare it numerically with the alternative scheme based on relative value iteration.

Cite

@article{arxiv.2206.03328,
  title  = {Concentration bounds for SSP Q-learning for average cost MDPs},
  author = {Shaan Ul Haque and Vivek Borkar},
  journal= {arXiv preprint arXiv:2206.03328},
  year   = {2022}
}

Comments

6 pages, 2 figures

R2 v1 2026-06-24T11:42:11.757Z