English
Related papers

Related papers: More Efficient Randomized Exploration for Reinforc…

200 papers

The empirically successful Thompson Sampling algorithm for stochastic bandits has drawn much interest in understanding its theoretical properties. One important benefit of the algorithm is that it allows domain knowledge to be conveniently…

Machine Learning · Computer Science 2016-07-22 Che-Yu Liu , Lihong Li

The classical theory of reinforcement learning (RL) has focused on tabular and linear representations of value functions. Further progress hinges on combining RL with modern function approximators such as kernel functions and deep neural…

Machine Learning · Computer Science 2021-01-01 Zhuoran Yang , Chi Jin , Zhaoran Wang , Mengdi Wang , Michael I. Jordan

This paper studies regret minimization with randomized value functions in reinforcement learning. In tabular finite-horizon Markov Decision Processes, we introduce a clipping variant of one classical Thompson Sampling (TS)-like algorithm,…

Machine Learning · Computer Science 2021-11-10 Priyank Agrawal , Jinglin Chen , Nan Jiang

Thompson sampling (TS) has optimal regret and excellent empirical performance in multi-armed bandit problems. Yet, in Bayesian optimization, TS underperforms popular acquisition functions (e.g., EI, UCB). TS samples arms according to the…

Machine Learning · Statistics 2024-12-02 David Sweet

Thompson sampling (TS) is one of the most popular and earliest algorithms to solve stochastic multi-armed bandit problems. We consider a variant of TS, named $\alpha$-TS, where we use a fractional or $\alpha$-posterior ($\alpha\in(0,1)$)…

Machine Learning · Statistics 2023-09-13 Prateek Jaiswal , Debdeep Pati , Anirban Bhattacharya , Bani K. Mallick

Thompson sampling is one of the most widely used algorithms for many online decision problems, due to its simplicity in implementation and superior empirical performance over other state-of-the-art methods. Despite its popularity and…

Machine Learning · Computer Science 2020-10-02 Tianyuan Jin , Pan Xu , Jieming Shi , Xiaokui Xiao , Quanquan Gu

The literature on bandit learning and regret analysis has focused on contexts where the goal is to converge on an optimal action in a manner that limits exploration costs. One shortcoming imposed by this orientation is that it does not…

Machine Learning · Computer Science 2017-05-01 Daniel Russo , David Tse , Benjamin Van Roy

We study algorithms using randomized value functions for exploration in reinforcement learning. This type of algorithms enjoys appealing empirical performance. We show that when we use 1) a single random seed in each episode, and 2) a…

Machine Learning · Computer Science 2022-10-14 Zhihan Xiong , Ruoqi Shen , Qiwen Cui , Maryam Fazel , Simon S. Du

Existing methods of combinatorial pure exploration mainly focus on the UCB approach. To make the algorithm efficient, they usually use the sum of upper confidence bounds within arm set $S$ to represent the upper confidence bound of $S$,…

Machine Learning · Computer Science 2022-06-22 Siwei Wang , Jun Zhu

This paper develops a viable notion of learning for sampling-based algorithms that applies in broader settings than previously considered. More specifically, we model a discounted infinite-horizon MDPs with Borel state and action spaces,…

Machine Learning · Statistics 2026-04-09 Daniel Adelman , Cagla Keceli , Alba V. Olivares-Nadal

This paper considers the use of a simple posterior sampling algorithm to balance between exploration and exploitation when learning to optimize actions such as in multi-armed bandit problems. The algorithm, also known as Thompson Sampling,…

Machine Learning · Computer Science 2014-02-04 Daniel Russo , Benjamin Van Roy

A challenging aspect of the bandit problem is that a stochastic reward is observed only for the chosen arm and the rewards of other arms remain missing. The dependence of the arm choice on the past context and reward pairs compounds the…

Machine Learning · Statistics 2023-05-02 Wonyoung Kim , Gi-soo Kim , Myunghee Cho Paik

Thompson Sampling is a principled method for balancing exploration and exploitation, but its real-world adoption faces computational challenges in large-scale or non-conjugate settings. While ensemble-based approaches offer partial…

Machine Learning · Computer Science 2025-10-29 Yingru Li , Jiawei Xu , Baoxiang Wang , Zhi-Quan Luo

We study the real-valued combinatorial pure exploration of the multi-armed bandit (R-CPE-MAB) problem. In R-CPE-MAB, a player is given $d$ stochastic arms, and the reward of each arm $s\in\{1, \ldots, d\}$ follows an unknown distribution…

Machine Learning · Computer Science 2023-11-16 Shintaro Nakamura , Masashi Sugiyama

Modern tasks in reinforcement learning have large state and action spaces. To deal with them efficiently, one often uses predefined feature mapping to represent states and actions in a low-dimensional space. In this paper, we study…

Machine Learning · Computer Science 2021-02-24 Dongruo Zhou , Jiafan He , Quanquan Gu

In model-based solution approaches to the problem of learning in an unknown environment, exploring to learn the model parameters takes a toll on the regret. The optimal performance with respect to regret or PAC bounds is achievable, if the…

Machine Learning · Computer Science 2015-10-13 P. Prasanna , Sarath Chandar , Balaraman Ravindran

Much of the recent literature on bandit learning focuses on algorithms that aim to converge on an optimal action. One shortcoming is that this orientation does not account for time sensitivity, which can play a crucial role when learning an…

Machine Learning · Computer Science 2020-01-09 Daniel Russo , Benjamin Van Roy

We consider Thompson Sampling (TS) for linear combinatorial semi-bandits and subgaussian rewards. We propose the first known TS whose finite-time regret does not scale exponentially with the dimension of the problem. We further show the…

Machine Learning · Statistics 2024-10-10 Raymond Zhang , Richard Combes

Thompson sampling is a widely used strategy for contextual bandits: at each round, it samples a reward function from a Bayesian posterior and acts greedily under that sample. Prior-data fitted networks (PFNs), such as TabPFN v2+ and TabICL…

Machine Learning · Statistics 2026-05-12 Yan Shuo Tan , Kenyon Ng , Ruizhe Deng , Sumetha Loganathan , Qiong Zhang , Bibhas Chakraborty

While quantum reinforcement learning (RL) has attracted a surge of attention recently, its theoretical understanding is limited. In particular, it remains elusive how to design provably efficient quantum RL algorithms that can address the…

Quantum Physics · Physics 2024-06-14 Han Zhong , Jiachen Hu , Yecheng Xue , Tongyang Li , Liwei Wang