English
Related papers

Related papers: On Regret Bounds of Thompson Sampling for Bayesian…

200 papers

Online reinforcement learning in infinite-horizon Markov decision processes (MDPs) remains less theoretically and algorithmically developed than its episodic counterpart, with many algorithms suffering from high ``burn-in'' costs and…

Machine Learning · Computer Science 2026-03-26 Guy Zamir , Matthew Zurek , Yudong Chen

We investigate the extent to which offline demonstration data can improve online learning. It is natural to expect some improvement, but the question is how, and by how much? We show that the degree of improvement must depend on the quality…

Machine Learning · Computer Science 2023-05-18 Botao Hao , Rahul Jain , Tor Lattimore , Benjamin Van Roy , Zheng Wen

In Bayesian optimization, Thompson sampling selects the evaluation point by sampling from the posterior distribution over the objective function maximizer. Because this sampling problem is intractable for Gaussian process (GP) surrogates,…

Machine Learning · Computer Science 2026-04-13 Donney Fan , Geoff Pleiss

We consider the problem of controlling an unknown linear quadratic Gaussian (LQG) system consisting of multiple subsystems connected over a network. Our goal is to minimize and quantify the regret (i.e. loss in performance) of our strategy…

Systems and Control · Electrical Eng. & Systems 2021-08-19 Sagar Sudhakara , Aditya Mahajan , Ashutosh Nayyar , Yi Ouyang

The multi-armed bandit (MAB) problem is a classical learning task that exemplifies the exploration-exploitation tradeoff. However, standard formulations do not take into account {\em risk}. In online decision making systems, risk is a…

Machine Learning · Computer Science 2020-08-04 Qiuyu Zhu , Vincent Y. F. Tan

We study a time-varying Bayesian optimization problem with bandit feedback, where the reward function belongs to a Reproducing Kernel Hilbert Space (RKHS). We approach the problem via an upper-confidence bound Gaussian Process algorithm,…

Optimization and Control · Mathematics 2025-10-27 Eliabelle Mauduit , Eloïse Berthier , Andrea Simonetto

In this work, we extend the concept of the $p$-mean welfare objective from social choice theory (Moulin 2004) to study $p$-mean regret in stochastic multi-armed bandit problems. The $p$-mean regret, defined as the difference between the…

Machine Learning · Computer Science 2024-12-18 Anand Krishna , Philips George John , Adarsh Barik , Vincent Y. F. Tan

We consider online sequential decision problems where an agent must balance exploration and exploitation. We derive a set of Bayesian `optimistic' policies which, in the stochastic multi-armed bandit case, includes the Thompson sampling…

Machine Learning · Statistics 2021-11-01 Brendan O'Donoghue , Tor Lattimore

Bayesian optimisation is a popular method for efficient optimisation of expensive black-box functions. Traditionally, BO assumes that the search space is known. However, in many problems, this assumption does not hold. To this end, we…

Machine Learning · Statistics 2026-04-28 Hung Tran-The , Sunil Gupta , Santu Rana , Huong Ha , Svetha Venkatesh

We present a new algorithm based on posterior sampling for learning in constrained Markov decision processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2023-09-28 Danil Provodin , Pratik Gajane , Mykola Pechenizkiy , Maurits Kaptein

We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We first analyze Boltzmann Q-learning with decaying temperature…

Machine Learning · Computer Science 2026-05-18 Rahul Singh , Siddharth Chandak , Eric Moulines , Vivek S. Borkar , Nicholas Bambos

We consider the exploration-exploitation tradeoff in linear quadratic (LQ) control problems, where the state dynamics is linear and the cost function is quadratic in states and controls. We analyze the regret of Thompson sampling (TS)…

Machine Learning · Statistics 2017-03-28 Marc Abeille , Alessandro Lazaric

We revisit the classic regret-minimization problem in the stochastic multi-armed bandit setting when the arm-distributions are allowed to be heavy-tailed. Regret minimization has been well studied in simpler settings of either bounded…

Machine Learning · Computer Science 2021-02-09 Shubhada Agrawal , Sandeep Juneja , Wouter M. Koolen

We consider stochastic multi-armed bandit problems with complex actions over a set of basic arms, where the decision maker plays a complex action rather than a basic arm in each round. The reward of the complex action is some function of…

Machine Learning · Statistics 2013-11-05 Aditya Gopalan , Shie Mannor , Yishay Mansour

We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes. Existing model-free algorithms achieve minimax worst-case regret, but their gap-dependent bounds remain…

Machine Learning · Statistics 2025-10-09 Haochen Zhang , Zhong Zheng , Lingzhou Xue

Bayesian optimization (BO) has well-documented merits for optimizing black-box functions with an expensive evaluation cost. Such functions emerge in applications as diverse as hyperparameter tuning, drug discovery, and robotics. BO hinges…

Machine Learning · Statistics 2026-05-28 Qin Lu , Konstantinos D. Polyzos , Bingcong Li , Georgios B. Giannakis

We study how to learn optimal interventions sequentially given causal information represented as a causal graph along with associated conditional distributions. Causal modeling is useful in real world problems like online advertisement…

Machine Learning · Statistics 2020-06-12 Yangyi Lu , Amirhossein Meisami , Ambuj Tewari , Zhenyu Yan

TWe establish regret lower bounds for adaptively controlling an unknown linear Gaussian system with quadratic costs. We combine ideas from experiment design, estimation theory and a perturbation bound of certain information matrices to…

Machine Learning · Computer Science 2024-06-13 Ingvar Ziemann , Henrik Sandberg

We propose a novel sparse spectrum approximation of Gaussian process (GP) tailored for Bayesian optimization. Whilst the current sparse spectrum methods provide desired approximations for regression problems, it is observed that this…

Machine Learning · Computer Science 2020-06-09 Ang Yang , Cheng Li , Santu Rana , Sunil Gupta , Svetha Venkatesh

We study the multi-objective linear contextual bandit problem, where multiple possible conflicting objectives must be optimized simultaneously. We propose \texttt{MOL-TS}, the \textit{first} Thompson Sampling algorithm with Pareto regret…

Machine Learning · Statistics 2025-12-02 Somangchan Park , Heesang Ann , Min-hwan Oh