paper-with-me

홈 › Papers

Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays

2015-06-02 · Junpei Komiyama, Junya Honda, Hiroshi Nakagawa

We discuss a multiple-play multi-armed bandit (MAB) problem in which several arms are selected at each round. Recently, Thompson sampling (TS), a randomized algorithm with a Bayesian spirit, has attracted much attention for its empirically excellent performance, and it is revealed to have an optimal regret bound in the standard single-play MAB problem. In this paper, we propose the multiple-play Thompson sampling (MP-TS) algorithm, an extension of TS to the multiple-play MAB problem, and discuss its regret analysis. We prove that MP-TS for binary rewards has the optimal regret upper bound that matches the regret lower bound provided by Anantharam et al. (1987). Therefore, MP-TS is the first computationally efficient algorithm with optimal regret. A set of computer simulations was also conducted, which compared MP-TS with state-of-the-art algorithms. We also propose a modification of MP-TS, which is shown to have better empirical performance.

📄 PDF Abstract BibTeX arXiv:1506.00779

Code (1)

jkomiyama/multiplaybanditlib 공식 구현

Tasks

Thompson Sampling

Methods 이 논문이 사용한 방법론

TS Spatio-temporal features extraction that measure the stabilty. The proposed method is based on a compression algorithm named Run Length Encoding. The workflow of the method is…

Similar Papers 제목 키워드 기반

Prior-free and prior-dependent regret bounds for Thompson Sampling

2013-04-21 · NeurIPS 2013 12 · Sébastien Bubeck, Che-Yu Liu

We consider the stochastic multi-armed bandit problem with a prior distribution on the reward distributions. We are interested in studying prior-free and prior-dependent regret bounds, very much in the same spirit as the…

Thompson Sampling

Thompson Sampling: An Asymptotically Optimal Finite Time Analysis

2012-05-18 · Emilie Kaufmann, Nathaniel Korda, Rémi Munos

The question of the optimality of Thompson Sampling for solving the stochastic multi-armed bandit problem had been open since 1933. In this paper we answer it positively for the case of Bernoulli rewards by providing the…

3D ReconstructionThompson Sampling

Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring

2020-06-17 · NeurIPS 2020 12 · Taira Tsuchiya, Junya Honda, Masashi Sugiyama

We investigate finite stochastic partial monitoring, which is a general model for sequential learning with limited feedback. While Thompson sampling is one of the most promising algorithms on a variety of online decision…

Decision MakingThompson Sampling

Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling

2019-12-06 · Cindy Trinh, Emilie Kaufmann, Claire Vernade, Richard Combes

Stochastic Rank-One Bandits (Katarya et al, (2017a,b)) are a simple framework for regret minimization problems over rank-one matrices of arms. The initially proposed algorithms are proved to have logarithmic regret, but …

Thompson Sampling

Thompson Sampling is Asymptotically Optimal in General Environments

2016-02-25 · Jan Leike, Tor Lattimore, Laurent Orseau, Marcus Hutter

We discuss a variant of Thompson sampling for nonparametric reinforcement learning in a countable classes of general stochastic environments. These environments can be non-Markov, non-ergodic, and partially observable. W…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Thompson Sampling