English
Related papers

Related papers: Information-Theoretic Minimax Regret Bounds for Re…

200 papers

We use the Reward Biased Maximum Likelihood Estimation (RBMLE) algorithm to learn optimal policies for constrained Markov Decision Processes (CMDPs). We analyze the learning regrets of RBMLE.

Optimization and Control · Mathematics 2021-05-31 Rahul Singh

We consider online reinforcement learning in episodic Markov decision process (MDP) with unknown transition function and stochastic rewards drawn from some fixed but unknown distribution. The learner aims to learn the optimal policy and…

Machine Learning · Computer Science 2024-03-12 Vincent Leon , S. Rasoul Etesami

Motivated by applications to online learning in sparse estimation and Bayesian optimization, we consider the problem of online unconstrained nonsubmodular minimization with delayed costs in both full information and bandit feedback…

Machine Learning · Computer Science 2022-06-02 Tianyi Lin , Aldo Pacchiano , Yaodong Yu , Michael I. Jordan

Green security domains feature defenders who plan patrols in the face of uncertainty about the adversarial behavior of poachers, illegal loggers, and illegal fishers. Importantly, the deterrence effect of patrols on adversaries' future…

Machine Learning · Computer Science 2021-06-17 Lily Xu , Andrew Perrault , Fei Fang , Haipeng Chen , Milind Tambe

We initiate the study of dynamic regret minimization for goal-oriented reinforcement learning modeled by a non-stationary stochastic shortest path problem with changing cost and transition functions. We start by establishing a lower bound…

Machine Learning · Computer Science 2022-05-27 Liyu Chen , Haipeng Luo

We address the issue of safety in reinforcement learning. We pose the problem in an episodic framework of a constrained Markov decision process. Existing results have shown that it is possible to achieve a reward regret of…

Machine Learning · Computer Science 2023-01-26 Tao Liu , Ruida Zhou , Dileep Kalathil , P. R. Kumar , Chao Tian

This paper investigates the problem of regret minimization for multi-armed bandit (MAB) problems with local differential privacy (LDP) guarantee. In stochastic bandit systems, the rewards may refer to the users' activities, which may…

Machine Learning · Computer Science 2020-07-08 Wenbo Ren , Xingyu Zhou , Jia Liu , Ness B. Shroff

We study algorithms for average-cost reinforcement learning problems with value function approximation. Our starting point is the recently proposed POLITEX algorithm, a version of policy iteration where the policy produced in each iteration…

Machine Learning · Computer Science 2019-08-29 Yasin Abbasi-Yadkori , Nevena Lazic , Csaba Szepesvari , Gellert Weisz

We study the offline data-driven sequential decision making problem in the framework of Markov decision process (MDP). In order to enhance the generalizability and adaptivity of the learned policy, we propose to evaluate each policy by a…

Statistics Theory · Mathematics 2021-11-11 Zhengling Qi , Peng Liao

Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and healthcare. To address this, Constrained Markov Decision Processes (CMDPs) are commonly used…

Machine Learning · Computer Science 2026-02-18 Chang Liu , Yunfan Li , Lin F. Yang

Recently, several studies (Zhou et al., 2021a; Zhang et al., 2021b; Kim et al., 2021; Zhou and Gu, 2022) have provided variance-dependent regret bounds for linear contextual bandits, which interpolates the regret for the worst-case regime…

Machine Learning · Computer Science 2023-02-22 Heyang Zhao , Jiafan He , Dongruo Zhou , Tong Zhang , Quanquan Gu

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

Information relaxation and duality in Markov decision processes have been studied recently by several researchers with the goal to derive dual bounds on the value function. In this paper we extend this dual formulation to controlled Markov…

Optimization and Control · Mathematics 2014-10-23 Fan Ye , Enlu Zhou

Traditional reinforcement learning usually assumes either episodic interactions with resets or continuous operation to minimize average or cumulative loss. While episodic settings have many theoretical results, resets are often unrealistic…

Optimization and Control · Mathematics 2026-01-13 Bianca Marin Moreno , Margaux Brégère , Pierre Gaillard , Nadia Oudjane

Obtaining no-regret guarantees for reinforcement learning (RL) in the case of problems with continuous state and/or action spaces is still one of the major open challenges in the field. Recently, a variety of solutions have been proposed,…

Machine Learning · Computer Science 2024-02-07 Davide Maran , Alberto Maria Metelli , Matteo Papini , Marcello Restell

Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized services, where users' sensitive and private information needs to be protected, we study regret minimization in finite-horizon Markov decision…

Machine Learning · Computer Science 2022-03-22 Xingyu Zhou

In several realistic situations, an interactive learning agent can practice and refine its strategy before going on to be evaluated. For instance, consider a student preparing for a series of tests. She would typically take a few practice…

Machine Learning · Computer Science 2017-06-08 Sudeep Raja Putta , Theja Tulabandhula

We propose a simple model selection approach for algorithms in stochastic bandit and reinforcement learning problems. As opposed to prior work that (implicitly) assumes knowledge of the optimal regret, we only require that each base…

Machine Learning · Computer Science 2020-12-25 Aldo Pacchiano , Christoph Dann , Claudio Gentile , Peter Bartlett

In this paper, we study the learning of safe policies in the setting of reinforcement learning problems. This is, we aim to control a Markov Decision Process (MDP) of which we do not know the transition probabilities, but we have access to…

Systems and Control · Electrical Eng. & Systems 2022-01-14 Santiago Paternain , Miguel Calvo-Fullana , Luiz F. O. Chamon , Alejandro Ribeiro

The expected regret of any reinforcement learning algorithm is lower bounded by $\Omega\left(\sqrt{DXAT}\right)$ for undiscounted returns, where $D$ is the diameter of the Markov decision process, $X$ the size of the state space, $A$ the…

Machine Learning · Computer Science 2024-06-10 Lucas Weber , Ana Bušić , Jiamin Zhu