English
Related papers

Related papers: Fine-Grained Gap-Dependent Bounds for Tabular MDPs…

200 papers

We provide an algorithm that achieves the optimal regret rate in an unknown weakly communicating Markov Decision Process (MDP). The algorithm proceeds in episodes where, in each episode, it picks a policy using regularization based on the…

Machine Learning · Computer Science 2012-05-14 Peter L. Bartlett , Ambuj Tewari

We consider the problem of learning in adversarial Markov decision processes [MDPs] with an oblivious adversary in a full-information setting. The agent interacts with an environment during $T$ episodes, each of which consists of $H$…

Machine Learning · Computer Science 2025-03-06 Daniil Tiapkin , Evgenii Chzhen , Gilles Stoltz

We consider a combinatorial multi-armed bandit problem for maximum value reward function under maximum value and index feedback. This is a new feedback structure that lies in between commonly studied semi-bandit and full-bandit feedback…

Machine Learning · Computer Science 2023-05-26 Yiliu Wang , Wei Chen , Milan Vojnović

Many real-world applications, such as those in medical domains, recommendation systems, etc, can be formulated as large state space reinforcement learning problems with only a small budget of the number of policy changes, i.e., low…

Machine Learning · Computer Science 2021-01-05 Minbo Gao , Tianle Xie , Simon S. Du , Lin F. Yang

We study gap-dependent performance guarantees for nearly minimax-optimal algorithms in reinforcement learning with linear function approximation. While prior works have established gap-dependent regret bounds in this setting, existing…

Machine Learning · Statistics 2026-02-25 Haochen Zhang , Zhong Zheng , Lingzhou Xue

We consider the setup of stochastic multi-armed bandits in the case when reward distributions are piecewise i.i.d. and bounded with unknown changepoints. We focus on the case when changes happen simultaneously on all arms, and in stark…

Machine Learning · Computer Science 2019-06-10 Subhojyoti Mukherjee , Odalric-Ambrym Maillard

We consider stochastic multi-armed bandits where the expected reward is a unimodal function over partially ordered arms. This important class of problems has been recently investigated in (Cope 2009, Yu 2011). The set of arms is either…

Machine Learning · Computer Science 2014-05-21 Richard Combes , Alexandre Proutiere

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

Machine Learning · Computer Science 2026-03-16 Antoine Moulin , Gergely Neu , Luca Viano

We present differentially private algorithms for the stochastic Multi-Armed Bandit (MAB) problem. This is a problem for applications such as adaptive clinical trials, experiment design, and user-targeted advertising where private…

Machine Learning · Statistics 2015-11-30 Aristide Tossou , Christos Dimitrakakis

In many real-world applications, it is hard to provide a reward signal in each step of a Reinforcement Learning (RL) process and more natural to give feedback when an episode ends. To this end, we study the recently proposed model of RL…

Machine Learning · Computer Science 2024-05-15 Asaf Cassel , Haipeng Luo , Aviv Rosenberg , Dmitry Sotnikov

We consider Markov Decision Processes (MDPs) where the rewards are unknown and may change in an adversarial manner. We provide an algorithm that achieves state-of-the-art regret bound of $O( \sqrt{\tau (\ln|S|+\ln|A|)T}\ln(T))$, where $S$…

Machine Learning · Computer Science 2019-05-28 Adrian Rivera Cardoso , He Wang , Huan Xu

In an episodic Markov Decision Process (MDP) problem, an online algorithm chooses from a set of actions in a sequence of $H$ trials, where $H$ is the episode length, in order to maximize the total payoff of the chosen actions. Q-learning,…

Machine Learning · Computer Science 2019-07-11 Xu Zhu

In this paper, we study the application of the Thompson sampling (TS) methodology to the stochastic combinatorial multi-armed bandit (CMAB) framework. We first analyze the standard TS algorithm for the general CMAB model when the outcome…

Machine Learning · Computer Science 2022-06-22 Siwei Wang , Wei Chen

We develop several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation. Using the optimism principle and assuming that the MDP has a linear structure, we…

Machine Learning · Computer Science 2021-04-27 Chen-Yu Wei , Mehdi Jafarnia-Jahromi , Haipeng Luo , Rahul Jain

We study the distribution of regret in stochastic multi-armed bandits and episodic reinforcement learning through a unified framework. We formalize a distributional regret bound as a probabilistic guarantee that holds uniformly over all…

Machine Learning · Computer Science 2026-05-08 Harin Lee , Min-hwan Oh

We study an important variant of the stochastic multi-armed bandit (MAB) problem, which takes penalization into consideration. Instead of directly maximizing cumulative expected reward, we need to balance between the total reward and…

Machine Learning · Statistics 2022-11-16 Guanhua Fang , Ping Li , Gennady Samorodnitsky

Autoregressive processes naturally arise in a large variety of real-world scenarios, including stock markets, sales forecasting, weather prediction, advertising, and pricing. When facing a sequential decision-making problem in such a…

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

We study stochastic decision-theoretic online learning with full information and event-level pure differential privacy. A COLT open problem of Hu and Mehta asks to determine the optimal gap-dependent regret rate for stochastic…

Machine Learning · Computer Science 2026-05-29 Tommaso Cesari , Roberto Colomboni

Past research on interactive decision making problems (bandits, reinforcement learning, etc.) mostly focuses on the minimax regret that measures the algorithm's performance on the hardest instance. However, an ideal algorithm should adapt…

Machine Learning · Computer Science 2023-06-13 Kefan Dong , Tengyu Ma
‹ Prev 1 3 4 5 6 7 10 Next ›