paper-with-me

Papers

Gradient Ascent for Active Exploration in Bandit Problems

2019-05-20 · Pierre Ménard

We present a new algorithm based on an gradient ascent for a general Active Exploration bandit problem in the fixed confidence setting. This problem encompasses several well studied problems such that the Best Arm Identification or Thresholding Bandits. It consists of a new sampling rule based on an online lazy mirror ascent. We prove that this algorithm is asymptotically optimal and, most importantly, computationally efficient.

📄 PDF Abstract BibTeX arXiv:1905.08165

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Meta-Learning Bandit Policies by Gradient Ascent

2020-06-09 · Branislav Kveton, Martin Mladenov, Chih-Wei Hsu, Manzil Zaheer 외

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment pa…

Meta-LearningMulti-Armed Bandits

Differentiable Linear Bandit Algorithm

2020-06-04 · Kaige Yang, Laura Toni

Upper Confidence Bound (UCB) is arguably the most commonly used method for linear multi-arm bandit problems. While conceptually and computationally simple, this method highly relies on the confidence bounds, failing to s…

Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature

2021-02-08 · NeurIPS 2021 12 · Kefan Dong, Jiaqi Yang, Tengyu Ma

This paper studies model-based bandit and reinforcement learning (RL) with nonlinear function approximations. We propose to study convergence to approximate local maxima because we show that global convergence is statist…

reinforcement-learningReinforcement Learning (RL)

Bayesian Unification of Gradient and Bandit-based Learning for Accelerated Global Optimisation

2017-05-28 · Ole-Christoffer Granmo

Bandit based optimisation has a remarkable advantage over gradient based approaches due to their global perspective, which eliminates the danger of getting stuck at local optima. However, for continuous optimisation prob…

Navigate

Best Arm Identification in Spectral Bandits

2020-05-20 · Tomáš Kocák, Aurélien Garivier

We study best-arm identification with fixed confidence in bandit models with graph smoothness constraint. We provide and analyze an efficient gradient ascent algorithm to compute the sample complexity of this problem as …