arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.05908cs.LGcs.SYeess.SY
收藏

面向不安分老虎机的更快Q学习算法

Faster Q-Learning Algorithms for Restless Bandits

IIIT Allahabad(阿拉哈巴德印度信息技术学院);IIT Madras(马德拉斯印度理工学院)

Parvish Kakarapalli, Devendra Kayande, Rahul Meshram

AI总结:

针对RMAB的Whittle指数学习,本文提出Q学习及其SQL、GSQL、PhaseQL变体并结合UCB探索,通过双时间尺度随机逼近和数值实验证明UCB加速收敛、PhaseQL收敛最优。

摘要:

我们研究用于不安分多臂老虎机(RMAB)的Whittle指数学习算法。我们首先提出Q学习算法及其变体——快速Q学习(SQL)、广义快速Q学习(GSQL)和阶段Q学习(PhaseQL)。我们还讨论了探索策略——ε-贪婪和上置信界(UCB)。我们将Q学习及其变体与UCB策略相结合的研究进行了扩展。通过数值算例说明,采用UCB探索策略的Q学习具有更快的收敛性,而采用UCB的PhaseQL具有最快的收敛速度。接下来,我们将Q学习变体的研究扩展到RMAB的指数学习。该指数学习算法是随机逼近的双时间尺度变体:在较慢时间尺度上更新指数学习方案,在较快时间尺度上假设指数值固定来更新Q学习。我们研究了恒定步长的双时间尺度随机逼近算法。通过数值算例描述了算法性能,结果表明结合UCB的Q学习指数学习比ε-贪婪收敛更快;此外,PhaseQL(结合UCB和ε-贪婪)相比其他Q学习算法具有最佳收敛性。

英文摘要:

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 -- $ε$-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 $ε$ greedy. Further, PhaseQL (with UCB and $ε$ greedy) has the best convergence than other Q-learning algorithms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑