English
Related papers

Related papers: Improved Bayesian Regret Bounds for Thompson Sampl…

200 papers

We consider reinforcement learning in an environment modeled by an episodic, finite, stage-dependent Markov decision process of horizon $H$ with $S$ states, and $A$ actions. The performance of an agent is measured by the regret after…

We study the Bayesian regret of the renowned Thompson Sampling algorithm in contextual bandits with binary losses and adversarially-selected contexts. We adapt the information-theoretic perspective of \cite{RvR16} to the contextual setting…

Machine Learning · Computer Science 2023-03-07 Gergely Neu , Julia Olkhovskaya , Matteo Papini , Ludovic Schwartz

Thompson Sampling has been widely used for contextual bandit problems due to the flexibility of its modeling power. However, a general theory for this class of methods in the frequentist setting is still lacking. In this paper, we present a…

Machine Learning · Computer Science 2021-10-05 Tong Zhang

Reinforcement learning (RL) has traditionally been understood from an episodic perspective; the concept of non-episodic RL, where there is no restart and therefore no reliable recovery, remains elusive. A fundamental question in…

Machine Learning · Computer Science 2021-05-31 Shuang Liu , Hao Su

We study the logistic bandit, in which rewards are binary with success probability $\exp(\beta a^\top \theta) / (1 + \exp(\beta a^\top \theta))$ and actions $a$ and coefficients $\theta$ are within the $d$-dimensional unit ball. While prior…

Machine Learning · Statistics 2019-05-14 Shi Dong , Tengyu Ma , Benjamin Van Roy

Understanding how to efficiently learn while adhering to safety constraints is essential for using online reinforcement learning in practical applications. However, proving rigorous regret bounds for safety-constrained reinforcement…

Machine Learning · Statistics 2025-04-29 Benjamin Schiffer , Lucas Janson

We consider the problem of transfer learning in an online setting. Different tasks are presented sequentially and processed by a within-task algorithm. We propose a lifelong learning strategy which refines the underlying data representation…

Machine Learning · Statistics 2019-10-14 Pierre Alquier , The Tien Mai , Massimiliano Pontil

In this paper, we investigate the performance of Thompson Sampling (TS) for online learning with censored feedback, focusing primarily on the classic repeated newsvendor model--a foundational framework in inventory management--and…

Machine Learning · Computer Science 2026-01-19 Li Chen , Hanzhang Qin , Yunbei Xu , Ruihao Zhu , Weizhou Zhang

Thompson Sampling is one of the most effective methods for contextual bandits and has been generalized to posterior sampling for certain MDP settings. However, existing posterior sampling methods for reinforcement learning are limited by…

Machine Learning · Computer Science 2022-08-24 Christoph Dann , Mehryar Mohri , Tong Zhang , Julian Zimmert

We study the problem of reinforcement learning from human feedback (RLHF), a critical problem in training large language models, from a theoretical perspective. Our main contribution is the design of novel sample-efficient RLHF algorithms…

Machine Learning · Computer Science 2025-08-11 Han Qi , Haochen Yang , Qiaosheng Zhang , Zhuoran Yang

This paper studies the safe reinforcement learning problem formulated as an episodic finite-horizon tabular constrained Markov decision process with an unknown transition kernel and stochastic reward and cost functions. We propose a…

Machine Learning · Computer Science 2024-10-15 Kihyun Yu , Duksang Lee , William Overman , Dabeen Lee

Building on the framework introduced by Xu and Raginksy [1] for supervised learning problems, we study the best achievable performance for model-based Bayesian reinforcement learning problems. With this purpose, we define minimum Bayesian…

Machine Learning · Computer Science 2022-07-19 Amaury Gouverneur , Borja Rodríguez-Gálvez , Tobias J. Oechtering , Mikael Skoglund

While numerous works have focused on devising efficient algorithms for reinforcement learning (RL) with uniformly bounded rewards, it remains an open question whether sample or time-efficient algorithms for RL with large state-action space…

Machine Learning · Computer Science 2024-03-08 Jiayi Huang , Han Zhong , Liwei Wang , Lin F. Yang

We study episodic reinforcement learning with fixed reward and transition functions, but with episode-dependent admissible action sets that are observed at the start of each episode. Performance is measured by cumulative regret against the…

Machine Learning · Computer Science 2026-05-18 Zijun Chen , Zihan Zhang

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

In this work, we close the fundamental gap of theory and practice by providing an improved regret bound for linear ensemble sampling. We prove that with an ensemble size logarithmic in $T$, linear ensemble sampling can achieve a frequentist…

Machine Learning · Statistics 2025-06-17 Harin Lee , Min-hwan Oh

In reinforcement learning the Q-values summarize the expected future rewards that the agent will attain. However, they cannot capture the epistemic uncertainty about those rewards. In this work we derive a new Bellman operator with…

Machine Learning · Computer Science 2022-12-07 Brendan O'Donoghue

Regret bounds in online learning compare the player's performance to $L^*$, the optimal performance in hindsight with a fixed strategy. Typically such bounds scale with the square root of the time horizon $T$. The more refined concept of…

Machine Learning · Computer Science 2018-02-12 Zeyuan Allen-Zhu , Sébastien Bubeck , Yuanzhi Li

We address the problem of the achievable regret rates with online logistic regression. We derive lower bounds with logarithmic regret under $L_1$, $L_2$, and $L_\infty$ constraints on the parameter values. The bounds are dominated by $d/2…

Machine Learning · Computer Science 2020-02-20 Gil I. Shamir

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-making problems,…

Machine Learning · Statistics 2021-06-11 Taira Tsuchiya , Junya Honda , Masashi Sugiyama