English

Q-learning as a monotone scheme

Machine Learning 2024-06-03 v1

Abstract

Stability issues with reinforcement learning methods persist. To better understand some of these stability and convergence issues involving deep reinforcement learning methods, we examine a simple linear quadratic example. We interpret the convergence criterion of exact Q-learning in the sense of a monotone scheme and discuss consequences of function approximation on monotonicity properties.

Keywords

Cite

@article{arxiv.2405.20538,
  title  = {Q-learning as a monotone scheme},
  author = {Lingyi Yang},
  journal= {arXiv preprint arXiv:2405.20538},
  year   = {2024}
}
R2 v1 2026-06-28T16:47:58.114Z