English
Related papers

Related papers: Optimal policy evaluation using kernel-based tempo…

200 papers

In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear function approximation for policy evaluation in discounted Markov decision processes. We show that a simple…

Machine Learning · Statistics 2024-06-18 Sergey Samsonov , Daniil Tiapkin , Alexey Naumov , Eric Moulines

We consider a class of statistical inverse problems involving the estimation of a regression operator from a Polish space to a separable Hilbert space, where the target lies in a vector-valued reproducing kernel Hilbert space induced by an…

Machine Learning · Statistics 2026-04-28 Jia-Qi Yang , Lei Shi

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

Machine Learning · Computer Science 2026-04-01 Abhishek Gupta , Aditya Mahajan

Here, we explore the problem of error propagation mitigation in modular digital twins as a sequential decision process. Building on a companion study that used a Hidden Markov Model (HMM) to infer latent error regimes from surrogate-physics…

Machine Learning · Computer Science 2026-04-27 Annice Najafi , Shokoufeh Mirzaei

We consider the problem of finding the best memoryless stochastic policy for an infinite-horizon partially observable Markov decision process (POMDP) with finite state and action spaces with respect to either the discounted or mean reward…

Optimization and Control · Mathematics 2022-05-02 Johannes Müller , Guido Montúfar

Many machine learning approaches for decision making, such as reinforcement learning, rely on simulators or predictive models to forecast the time-evolution of quantities of interest, e.g., the state of an agent or the reward of a policy.…

Machine Learning · Computer Science 2024-01-17 Petar Bevanda , Max Beier , Armin Lederer , Stefan Sosnowski , Eyke Hüllermeier , Sandra Hirche

This paper considers the problem of finding near-optimal Markovian randomized (MR) policies for finite-state-action, infinite-horizon, constrained risk-sensitive Markov decision processes (CRSMDPs). Constraints are in the form of standard…

Optimization and Control · Mathematics 2023-03-14 Uday Kumar M , Sanjay P Bhat , Veeraruna Kavitha , Nandyala Hemachandra

Constrained partially observable Markov decision processes (CPOMDPs) have been used to model various real-world phenomena. However, they are notoriously difficult to solve to optimality, and there exist only a few approximation methods for…

Artificial Intelligence · Computer Science 2023-06-27 Robert K. Helmeczi , Can Kavaklioglu , Mucahit Cevik

In this paper we provide faster algorithms for approximately solving discounted Markov Decision Processes in multiple parameter regimes. Given a discounted Markov Decision Process (DMDP) with $|S|$ states, $|A|$ actions, discount factor…

Data Structures and Algorithms · Computer Science 2020-12-24 Aaron Sidford , Mengdi Wang , Xian Wu , Yinyu Ye

Online reinforcement learning in infinite-horizon Markov decision processes (MDPs) remains less theoretically and algorithmically developed than its episodic counterpart, with many algorithms suffering from high ``burn-in'' costs and…

Machine Learning · Computer Science 2026-03-26 Guy Zamir , Matthew Zurek , Yudong Chen

In this paper, we deal with nonparametric regression for circular data, meaning that observations are represented by points lying on the unit circle. We propose a kernel estimation procedure with data-driven selection of the bandwidth…

Statistics Theory · Mathematics 2023-07-03 Tien Dat Nguyen , Thanh Mai Pham Ngoc , Vincent Rivoirard

The problem of establishing out-of-sample bounds for the values of an unkonwn ground-truth function is considered. Kernels and their associated Hilbert spaces are the main formalism employed herein along with an observational model where…

Machine Learning · Computer Science 2022-09-13 Paul Scharnhorst , Emilio T. Maddalena , Yuning Jiang , Colin N. Jones

It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Markov decision processes (POMDPs), optimal memoryless policies…

Optimization and Control · Mathematics 2016-02-16 Guido Montufar , Keyan Ghazi-Zahedi , Nihat Ay

We consider the data-driven approximation of the Koopman operator for stochastic differential equations on reproducing kernel Hilbert spaces (RKHS). Our focus is on the estimation error if the data are collected from long-term ergodic…

Dynamical Systems · Mathematics 2023-12-20 Friedrich Philipp , Manuel Schaller , Karl Worthmann , Sebastian Peitz , Feliks Nüske

We propose a new technique for constructing low-rank approximations of matrices that arise in kernel methods for machine learning. Our approach pairs a novel automatically constructed analytic expansion of the underlying kernel function…

Machine Learning · Computer Science 2022-02-09 John Paul Ryan , Anil Damle

There has been growing progress on theoretical analyses for provably efficient learning in MDPs with linear function approximation, but much of the existing work has made strong assumptions to enable exploration by conventional exploration…

Machine Learning · Computer Science 2020-10-23 Andrea Zanette , Alessandro Lazaric , Mykel J. Kochenderfer , Emma Brunskill

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 investigate a simple objective for nonlinear instrumental variable (IV) regression based on a kernelized conditional moment restriction (CMR) known as a maximum moment restriction (MMR). The MMR objective is formulated by maximizing the…

Machine Learning · Computer Science 2023-02-10 Rui Zhang , Masaaki Imaizumi , Bernhard Schölkopf , Krikamol Muandet

We study the Stochastic Shortest Path (SSP) problem with a linear mixture transition kernel, where an agent repeatedly interacts with a stochastic environment and seeks to reach certain goal state while minimizing the cumulative cost.…

Machine Learning · Computer Science 2024-02-15 Qiwei Di , Jiafan He , Dongruo Zhou , Quanquan Gu

There are two primary approaches to solving Markov decision problems (MDPs): dynamic programming based on the Bellman equation and linear programming (LP). Dynamic programming methods are the most widely used and form the foundation of both…

Artificial Intelligence · Computer Science 2026-02-24 Donghwan Lee , Hyukjun Yang , Bum Geun Park