English
Related papers

Related papers: Minimax Optimal Variance-Aware Regret Bounds for M…

200 papers

Partial monitoring is a general model for sequential learning with limited feedback formalized as a game between two players. In this game, the learner chooses an action and at the same time the opponent chooses an outcome, then the learner…

Machine Learning · Statistics 2015-10-01 Junpei Komiyama , Junya Honda , Hiroshi Nakagawa

This work considers the sample complexity of obtaining an $\varepsilon$-optimal policy in an average reward Markov Decision Process (AMDP), given access to a generative model (simulator). When the ground-truth MDP is weakly communicating,…

Machine Learning · Computer Science 2022-12-02 Jinghan Wang , Mengdi Wang , Lin F. Yang

We present an efficient reinforcement learning algorithm that learns the optimal admission control policy in a partially observable queueing network. Specifically, only the arrival and departure times from the network are observable, and…

Machine Learning · Computer Science 2023-08-07 Jonatha Anselmi , Bruno Gaujal , Louis-Sébastien Rebuffi

Recent studies have shown that reinforcement learning with KL-regularized objectives can enjoy faster rates of convergence or logarithmic regret, in contrast to the classical $\sqrt{T}$-type regret in the unregularized setting. However, the…

Machine Learning · Computer Science 2026-03-03 Kaixuan Ji , Qingyue Zhao , Heyang Zhao , Qiwei Di , Quanquan Gu

Despite rapid progress in theoretical reinforcement learning (RL) over the last few years, most of the known guarantees are worst-case in nature, failing to take advantage of structure that may be known a priori about a given RL problem at…

Machine Learning · Computer Science 2021-10-26 Noah Golowich , Ankur Moitra

Policy design in non-stationary Markov Decision Processes (MDPs) is inherently challenging due to the complexities introduced by time-varying system transition and reward, which make it difficult for learners to determine the optimal…

Machine Learning · Computer Science 2025-11-17 Ziyi Zhang , Yorie Nakahira , Guannan Qu

In average reward Markov decision processes, state-of-the-art algorithms for regret minimization follow a well-established framework: They are model-based, optimistic and episodic. First, they maintain a confidence region from which…

Machine Learning · Computer Science 2025-12-01 Victor Boone , Bruno Gaujal

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 study the problem of adaptive control of the stochastic linear quadratic regulator (LQR) with constraints that must be satisfied at every time step. Prior work on the multidimensional problem has shown $\tilde{O}(T^{2/3})$ regret and…

Optimization and Control · Mathematics 2026-05-08 Spencer Hutchinson , Nanfei Jiang , Mahnoosh Alizadeh

In this paper, we revisit the online non-monotone continuous DR-submodular maximization problem over a down-closed convex set, which finds wide real-world applications in the domain of machine learning, economics, and operations research.…

Machine Learning · Computer Science 2022-08-17 Qixin Zhang , Zengde Deng , Zaiyi Chen , Kuangqi Zhou , Haoyuan Hu , Yu Yang

We study the $K$-armed logistic bandit problem, where at each round, the agent observes $K$ feature vectors associated with $K$ actions. Existing approaches that achieve a rate-optimal $\tilde{\mathcal{O}}(\sqrt{dT})$ regret bound rely…

Machine Learning · Computer Science 2026-05-01 Seoungbin Bae , Dabeen Lee

Stochastic linear bandits are a fundamental model for sequential decision making, where an agent selects a vector-valued action and receives a noisy reward with expected value given by an unknown linear function. Although well studied in…

Machine Learning · Computer Science 2025-06-23 Bruce Huang , Ruida Zhou , Lin F. Yang , Suhas Diggavi

We study reinforcement learning with linear function approximation, unknown transition, and adversarial losses in the bandit feedback setting. Specifically, we focus on linear mixture MDPs whose transition kernel is a linear mixture model.…

Machine Learning · Computer Science 2024-03-08 Long-Fei Li , Peng Zhao , Zhi-Hua Zhou

We study batch learning with log-loss in the individual setting, where the outcome sequence is deterministic. Because empirical statistics are not directly applicable in this regime, obtaining regret guarantees for batch learning has long…

Information Theory · Computer Science 2025-11-18 Yaniv Fogel , Meir Feder

We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\Lambda$ steps per episode. This model captures environments that are stable except at a few…

Machine Learning · Computer Science 2026-02-11 Ofir Schlisselberg , Tal Lancewicki , Yishay Mansour

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 study reinforcement learning in an infinite-horizon average-reward setting with linear function approximation, where the transition probability function of the underlying Markov Decision Process (MDP) admits a linear form over a feature…

Machine Learning · Computer Science 2022-05-11 Yue Wu , Dongruo Zhou , Quanquan Gu

We study a sequential decision problem where the learner faces a sequence of $K$-armed bandit tasks. The task boundaries might be known (the bandit meta-learning setting), or unknown (the non-stationary bandit setting). For a given integer…

We consider the problem of online combinatorial optimization under semi-bandit feedback, where a learner has to repeatedly pick actions from a combinatorial decision set in order to minimize the total losses associated with its decisions.…

Machine Learning · Computer Science 2015-06-11 Gergely Neu

We study the constant regret guarantees in reinforcement learning (RL). Our objective is to design an algorithm that incurs only finite regret over infinite episodes with high probability. We introduce an algorithm, Cert-LSVI-UCB, for…

Machine Learning · Computer Science 2024-12-13 Weitong Zhang , Zhiyuan Fan , Jiafan He , Quanquan Gu