paper-with-me

Papers

Thompson Sampling with Diffusion Generative Prior

2023-01-12 · Yu-Guan Hsieh, Shiva Prasad Kasiviswanathan, Branislav Kveton, Patrick Blöbaum

In this work, we initiate the idea of using denoising diffusion models to learn priors for online decision making problems. Our special focus is on the meta-learning for bandit framework, with the goal of learning a strategy that performs well across bandit tasks of a same class. To this end, we train a diffusion model that learns the underlying task distribution and combine Thompson sampling with the learned prior to deal with new tasks at test time. Our posterior sampling algorithm is designed to carefully balance between the learned prior and the noisy observations that come from the learner's interaction with the environment. To capture realistic bandit scenarios, we also propose a novel diffusion model training procedure that trains even from incomplete and/or noisy data, which could be of independent interest. Finally, our extensive experimental evaluations clearly demonstrate the potential of the proposed approach.

📄 PDF Abstract BibTeX arXiv:2301.05182

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingDenoisingMeta-LearningThompson Sampling

Methods 이 논문이 사용한 방법론

Test 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Racing Thompson: an Efficient Algorithm for Thompson Sampling with Non-conjugate Priors

2017-08-16 · ICML 2018 7 · Yichi Zhou, Jun Zhu, Jingwei Zhuo

Thompson sampling has impressive empirical performance for many multi-armed bandit problems. But current algorithms for Thompson sampling only work for the case of conjugate priors since these algorithms require to infer…

Thompson Sampling

Regenerative Particle Thompson Sampling

2022-03-15 · Zeyu Zhou, Bruce Hajek, Nakjung Choi, Anwar Walid

This paper proposes regenerative particle Thompson sampling (RPTS), a flexible variation of Thompson sampling. Thompson sampling itself is a Bayesian heuristic for solving stochastic bandit problems, but it is hard to im…

Thompson Sampling

Thompson Sampling for Linear Bandit Problems with Normal-Gamma Priors

2023-03-06 · Björn Lindenberg, Karl-Olof Lindahl

We consider Thompson sampling for linear bandit problems with finitely many independent arms, where rewards are sampled from normal distributions that are linearly dependent on unknown parameter vectors and with unknown …

Thompson Sampling

Diffusion Approximations for Thompson Sampling

2021-05-19 · Lin Fan, Peter W. Glynn

We study the behavior of Thompson sampling from the perspective of weak convergence. In the regime with small $\gamma > 0$, where the gaps between arm means scale as $\sqrt{\gamma}$ and over time horizons that scale as $…

Multi-Armed BanditsThompson Sampling

Adaptive Thompson Sampling Stacks for Memory Bounded Open-Loop Planning

2019-07-11 · Thomy Phan, Thomas Gabor, Robert Müller, Christoph Roch 외

We propose Stable Yet Memory Bounded Open-Loop (SYMBOL) planning, a general memory bounded approach to partially observable open-loop planning. SYMBOL maintains an adaptive stack of Thompson Sampling bandits, whose size …

Thompson Sampling