paper-with-me

홈 › Papers

Regularized-OFU: an efficient algorithm for general contextual bandit with optimization oracles

2021-09-29 · Yichi Zhou, Shihong Song, Huishuai Zhang, Jun Zhu, Wei Chen, Tie-Yan Liu

In contextual bandit, one major challenge is to develop theoretically solid and empirically efficient algorithms for general function classes. We present a novel algorithm called \emph{regularized optimism in face of uncertainty (ROFU)} for general contextual bandit problems. It exploits an optimization oracle to calculate the well-founded upper confidence bound (UCB). Theoretically, for general function classes under very mild assumptions, it achieves a near-optimal regret bound $\Tilde{O}(\sqrt{T})$. Practically, one great advantage of ROFU is that the optimization oracle can be efficiently implemented with low computational cost. Thus, we can easily extend ROFU for contextual bandits with deep neural networks as the function class, which outperforms strong baselines including the UCB and Thompson sampling variants.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed BanditsThompson Sampling

Similar Papers 제목 키워드 기반

Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit

2021-06-29 · Yichi Zhou, Shihong Song, Huishuai Zhang, Jun Zhu 외

Balancing exploration and exploitation (EE) is a fundamental problem in contex-tual bandit. One powerful principle for EE trade-off isOptimism in Face of Uncer-tainty(OFU), in which the agent takes the action according t…

Multi-Armed Bandits

Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits

2023-06-13 · Lequn Wang, Akshay Krishnamurthy, Aleksandrs Slivkins

We consider offline policy optimization (OPO) in contextual bandits, where one is given a fixed dataset of logged interactions. While pessimistic regularizers are typically used to mitigate distribution shift, prior impl…

Multi-Armed Bandits

Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification

2026-06-04 · Haoyang Hong, Zichen Wang, Quanquan Gu, Huazheng Wang arxiv

We study KL-regularized contextual bandits and episodic reinforcement learning (RL) under general function approximation with model misspecification. Existing guarantees rely on realizability and therefore do not extend …

Reinforcement Learning

Surrogate Objectives for Batch Policy Optimization in One-step Decision Making

2019-12-01 · NeurIPS 2019 12 · Minmin Chen, Ramki Gummadi, Chris Harris, Dale Schuurmans

We investigate batch policy optimization for cost-sensitive classification and contextual bandits---two related tasks that obviate exploration but require generalizing from observed rewards to action selections in unseen…

Decision MakingMulti-Armed Bandits

Regularized Contextual Bandits

2018-10-11 · Xavier Fontaine, Quentin Berthet, Vianney Perchet

We consider the stochastic contextual bandit problem with additional regularization. The motivation comes from problems where the policy of the agent must be close to some baseline policy which is known to perform well o…

Multi-Armed Bandits