paper-with-me

Papers

A Diffusion Analysis of Policy Gradient for Stochastic Bandits

2026-03-10 · Tor Lattimore arxiv

We study a continuous-time diffusion approximation of policy gradient for $k$-armed stochastic bandits. We prove that with a learning rate $η= O(Δ^2/\log(n))$ the regret is $O(k \log(k) \log(n) / η)$ where $n$ is the horizon and $Δ$ the minimum gap. Moreover, we construct an instance with only logarithmically many arms for which the regret is linear unless $η= O(Δ^2)$.

📄 PDF Abstract BibTeX arXiv:2603.10219

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Lyapunov Analysis of Softmax Policy Gradient for Stochastic Bandits

2026-03-27 · Tor Lattimore arxiv

We adapt the analysis of policy gradient for continuous time $k$-armed stochastic bandits by Lattimore (2026) to the standard discrete time setup. As in continuous time, we prove that with learning rate $η= O(Δ_{\min}^2/…

Stochastic Gradient Succeeds for Bandits

2024-02-27 · Jincheng Mei, Zixin Zhong, Bo Dai, Alekh Agarwal 외

We show that the \emph{stochastic gradient} bandit algorithm converges to a \emph{globally optimal} policy at an $O(1/t)$ rate, even with a \emph{constant} step size. Remarkably, global convergence of the stochastic grad…

A Short Note on Soft-max and Policy Gradients in Bandits Problems

2020-07-20 · Neil Walton

This is a short communication on a Lyapunov function argument for softmax in bandit problems. There are a number of excellent papers coming out using differential equations for policy gradient algorithms in reinforcement…

reinforcement-learningReinforcement Learning (RL)

An Efficient Algorithm for Deep Stochastic Contextual Bandits

2021-04-12 · Tan Zhu, Guannan Liang, Chunjiang Zhu, Haining Li 외

In stochastic contextual bandit (SCB) problems, an agent selects an action based on certain observed context to maximize the cumulative reward over iterations. Recently there have been a few studies using a deep neural n…

Multi-Armed BanditsStochastic Optimization

Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates

2025-02-11 · Jincheng Mei, Bo Dai, Alekh Agarwal, Sharan Vaswani 외

We provide a new understanding of the stochastic gradient bandit algorithm by showing that it converges to a globally optimal policy almost surely using \emph{any} constant learning rate. This result demonstrates that th…