paper-with-me

Papers

Meta-Thompson Sampling

2021-02-11 · Branislav Kveton, Mikhail Konobeev, Manzil Zaheer, Chih-Wei Hsu, Martin Mladenov, Craig Boutilier, Csaba Szepesvari

Efficient exploration in bandits is a fundamental online learning problem. We propose a variant of Thompson sampling that learns to explore better as it interacts with bandit instances drawn from an unknown prior. The algorithm meta-learns the prior and thus we call it MetaTS. We propose several efficient implementations of MetaTS and analyze it in Gaussian bandits. Our analysis shows the benefit of meta-learning and is of a broader interest, because we derive a novel prior-dependent Bayes regret bound for Thompson sampling. Our theory is complemented by empirical evaluation, which shows that MetaTS quickly adapts to the unknown prior.

📄 PDF Abstract BibTeX arXiv:2102.06129

Code (0)

등록된 구현이 없습니다.

Tasks

Efficient ExplorationMeta-LearningMulti-Armed BanditsThompson Sampling

Similar Papers 제목 키워드 기반

Modified Meta-Thompson Sampling for Linear Bandits and Its Bayes Regret Analysis

2024-09-10 · Hao Li, Dong Liang, Zheng Xie

Meta-learning is characterized by its ability to learn how to learn, enabling the adaptation of learning strategies across different tasks. Recent research introduced the Meta-Thompson Sampling (Meta-TS), which meta-lear…

Meta-LearningMulti-Armed BanditsThompson Sampling

Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs

2025-10-06 · Runlin Zhou, Chixiang Chen, Elynn Chen arxiv

We study meta-reinforcement learning in finite-horizon MDPs where related tasks share similar structures in their optimal action-value functions. Specifically, we posit a linear representation $Q^*_h(s,a)=Φ_h(s,a)\,θ^{(k…

Reinforcement Learning

Memory Sequence Length of Data Sampling Impacts the Adaptation of Meta-Reinforcement Learning Agents

2024-06-18 · Menglong Zhang, Fuyuan Qian, Quanying Liu

Fast adaptation to new tasks is extremely important for embodied agents in the real world. Meta-reinforcement learning (meta-RL) has emerged as an effective method to enable fast adaptation in unknown environments. Compa…

continuous-controlContinuous ControlMeta Reinforcement LearningMuJoCo+1

Meta Dynamic Pricing: Transfer Learning Across Experiments

2019-02-28 · Hamsa Bastani, David Simchi-Levi, Ruihao Zhu

We study the problem of learning shared structure \emph{across} a sequence of dynamic pricing experiments for related products. We consider a practical formulation where the unknown demand parameters for each product com…

Thompson SamplingTransfer Learning

Thompson sampling with the online bootstrap

2014-10-15 · Dean Eckles, Maurits Kaptein

Thompson sampling provides a solution to bandit problems in which new observations are allocated to arms with the posterior probability that an arm is optimal. While sometimes easy to implement and asymptotically optimal…

Thompson Sampling