English

Faster Q-Learning Algorithms for Restless Bandits

Machine Learning 2024-09-11 v1 Systems and Control Systems and Control

Abstract

We study the Whittle index learning algorithm for restless multi-armed bandits (RMAB). We first present Q-learning algorithm and its variants -- speedy Q-learning (SQL), generalized speedy Q-learning (GSQL) and phase Q-learning (PhaseQL). We also discuss exploration policies -- ϵ\epsilon-greedy and Upper confidence bound (UCB). We extend the study of Q-learning and its variants with UCB policy. We illustrate using numerical example that Q-learning with UCB exploration policy has faster convergence and PhaseQL with UCB have fastest convergence rate. We next extend the study of Q-learning variants for index learning to RMAB. The algorithm of index learning is two-timescale variant of stochastic approximation, on slower timescale we update index learning scheme and on faster timescale we update Q-learning assuming fixed index value. We study constant stepsizes two timescale stochastic approximation algorithm. We describe the performance of our algorithms using numerical example. It illustrate that index learning with Q learning with UCB has faster convergence that ϵ\epsilon greedy. Further, PhaseQL (with UCB and ϵ\epsilon greedy) has the best convergence than other Q-learning algorithms.

Keywords

Cite

@article{arxiv.2409.05908,
  title  = {Faster Q-Learning Algorithms for Restless Bandits},
  author = {Parvish Kakarapalli and Devendra Kayande and Rahul Meshram},
  journal= {arXiv preprint arXiv:2409.05908},
  year   = {2024}
}

Comments

7 pages, 3 figures, conference. arXiv admin note: substantial text overlap with arXiv:2409.04605

R2 v1 2026-06-28T18:38:59.664Z