English
Related papers

Related papers: Posterior Sampling-based Online Learning for Episo…

200 papers

We study the problem of infinite-horizon average-reward reinforcement learning with linear Markov decision processes (MDPs). The associated Bellman operator of the problem not being a contraction makes the algorithm design challenging.…

Machine Learning · Statistics 2025-03-12 Kihyuk Hong , Woojin Chae , Yufan Zhang , Dabeen Lee , Ambuj Tewari

We study the sample complexity of online reinforcement learning in the general \hzyrev{non-episodic} setting of nonlinear dynamical systems with continuous state and action spaces. Our analysis accommodates a large class of dynamical…

Machine Learning · Computer Science 2026-03-02 Michael Muehlebach , Zhiyu He , Michael I. Jordan

We consider reinforcement learning for continuous-time Markov decision processes (MDPs) in the infinite-horizon, average-reward setting. In contrast to discrete-time MDPs, a continuous-time process moves to a state and stays there for a…

Machine Learning · Computer Science 2024-07-03 Xuefeng Gao , Xun Yu Zhou

We consider online learning in episodic loop-free Markov decision processes (MDPs), where the loss function can change arbitrarily between episodes, and the transition function is not known to the learner. We show…

Machine Learning · Computer Science 2019-05-21 Aviv Rosenberg , Yishay Mansour

This paper studies multi-stage systems with end-to-end bandit feedback. In such systems, each job needs to go through multiple stages, each managed by a different agent, before generating an outcome. Each agent can only control its own…

Machine Learning · Computer Science 2024-08-20 I-Hong Hou

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

Any reinforcement learning algorithm that applies to all Markov decision processes (MDPs) will suffer $\Omega(\sqrt{SAT})$ regret on some MDP, where $T$ is the elapsed time and $S$ and $A$ are the cardinalities of the state and action…

Machine Learning · Statistics 2014-11-04 Ian Osband , Benjamin Van Roy

This work pioneers regret analysis of risk-sensitive reinforcement learning in partially observable environments with hindsight observation, addressing a gap in theoretical exploration. We introduce a novel formulation that integrates…

Machine Learning · Computer Science 2024-02-29 Tonghe Zhang , Yu Chen , Longbo Huang

We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. Compared to prior work, our bounds depend on alternative definitions of gaps. These definitions are based on the…

Machine Learning · Computer Science 2021-10-27 Christoph Dann , Teodor V. Marinov , Mehryar Mohri , Julian Zimmert

We propose an epoch-based reinforcement learning algorithm for infinite-horizon average-cost Markov decision processes (MDPs) that leverages a partial order over a policy class. In this structure, $\pi' \leq \pi$ if data collected under…

Machine Learning · Statistics 2025-08-07 Zhongjun Zhang , Shipra Agrawal , Ilan Lobel , Sean R. Sinclair , Christina Lee Yu

The online Markov decision process (MDP) is a generalization of the classical Markov decision process that incorporates changing reward functions. In this paper, we propose practical online MDP algorithms with policy iteration and…

Machine Learning · Computer Science 2015-10-16 Yao Ma , Hao Zhang , Masashi Sugiyama

Restless bandit problems assume time-varying reward distributions of the arms, which adds flexibility to the model but makes the analysis more challenging. We study learning algorithms over the unknown reward distributions and prove a…

Machine Learning · Computer Science 2019-10-15 Young Hun Jung , Marc Abeille , Ambuj Tewari

We consider undiscounted reinforcement learning in Markov decision processes (MDPs) where both the reward functions and the state-transition probabilities may vary (gradually or abruptly) over time. For this problem setting, we propose an…

Machine Learning · Computer Science 2019-09-11 Pratik Gajane , Ronald Ortner , Peter Auer

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 online learning an algorithm plays against an environment with losses possibly picked by an adversary at each round. The generality of this framework includes problems that are not adversarial, for example offline optimization, or saddle…

Machine Learning · Computer Science 2021-02-04 Ryan D'Orazio , Ruitong Huang

Online learning methods yield sequential regret bounds under minimal assumptions and provide in-expectation risk bounds for statistical learning. However, despite the apparent advantage of online guarantees over their statistical…

Machine Learning · Computer Science 2023-08-16 Dirk van der Hoeven , Nikita Zhivotovskiy , Nicolò Cesa-Bianchi

We consider the online version of the isotonic regression problem. Given a set of linearly ordered points (e.g., on the real line), the learner must predict labels sequentially at adversarially chosen positions and is evaluated by her total…

Machine Learning · Computer Science 2016-10-10 Wojciech Kotłowski , Wouter M. Koolen , Alan Malek

Bayesian approaches provide a principled solution to the exploration-exploitation trade-off in Reinforcement Learning. Typical approaches, however, either assume a fully observable environment or scale poorly. This work introduces the…

Artificial Intelligence · Computer Science 2018-11-15 Sammie Katt , Frans Oliehoek , Christopher Amato

We study various discrete nonlinear combinatorial optimization problems in an online learning framework. In the first part, we address the question of whether there are negative results showing that getting a vanishing (or even vanishing…

Data Structures and Algorithms · Computer Science 2020-06-24 Evripidis Bampis , Dimitris Christou , Bruno Escoffier , Nguyen Kim Thang

Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from a mentor and…

Machine Learning · Computer Science 2025-09-17 Benjamin Plaut , Juan Liévano-Karim , Hanlin Zhu , Stuart Russell