English
Related papers

Related papers: Stochastic Approximation for Risk-aware Markov Dec…

200 papers

We extend the Longstaff-Schwartz algorithm for approximately solving optimal stopping problems on high-dimensional state spaces. We reformulate the optimal stopping problem for Markov processes in discrete time as a generalized statistical…

Probability · Mathematics 2007-05-23 Daniel Egloff

The goal of this paper is to analyze distributional Markov Decision Processes as a class of control problems in which the objective is to learn policies that steer the distribution of a cumulative reward toward a prescribed target law,…

Optimization and Control · Mathematics 2026-02-09 Nicole Bäuerle , Athanasios Vasileiadis

We study the so-called two-time-scale stochastic approximation, a simulation-based approach for finding the roots of two coupled nonlinear operators. Our focus is to characterize its finite-time performance in a Markov setting, which often…

Optimization and Control · Mathematics 2021-04-06 Thinh T. Doan

Nowadays, algorithms with fast convergence, small memory footprints, and low per-iteration complexity are particularly favorable for artificial intelligence applications. In this paper, we propose a doubly stochastic algorithm with a novel…

Machine Learning · Computer Science 2023-04-25 Zebang Shen , Hui Qian , Tongzhou Mu , Chao Zhang

Motivated by applications in reinforcement learning (RL), we study a nonlinear stochastic approximation (SA) algorithm under Markovian noise, and establish its finite-sample convergence bounds under various stepsizes. Specifically, we show…

Optimization and Control · Mathematics 2022-01-27 Zaiwei Chen , Sheng Zhang , Thinh T. Doan , John-Paul Clarke , Siva Theja Maguluri

For a risk-averse finite-horizon Markov Decision Problem, we introduce a special class of Markov coherent risk measures, called mini-batch measures. We also define the class of multipattern risk-averse problems that generalizes the class of…

Machine Learning · Computer Science 2026-05-04 Andrzej Ruszczynski , Tiangang Zhang

We consider large-scale Markov decision processes (MDPs) with an unknown cost function and employ stochastic convex optimization tools to address the problem of imitation learning, which consists of learning a policy from a finite set of…

Machine Learning · Computer Science 2022-01-04 Angeliki Kamoutsi , Goran Banjac , John Lygeros

This article presents a constrained policy optimization approach for the optimal control of systems under nonstationary uncertainties. We introduce an assumption that we call Markov embeddability that allows us to cast the stochastic…

Optimization and Control · Mathematics 2026-05-11 Sungho Shin , François Pacaud , Emil Contantinescu , Mihai Anitescu

SARSA is an on-policy algorithm to learn a Markov decision process policy in reinforcement learning. We investigate the SARSA algorithm with linear function approximation under the non-i.i.d.\ data, where a single sample trajectory is…

Machine Learning · Computer Science 2019-11-20 Shaofeng Zou , Tengyu Xu , Yingbin Liang

Stochastic approximation is a foundation for many algorithms found in machine learning and optimization. It is in general slow to converge: the mean square error vanishes as $O(n^{-1})$. A deterministic counterpart known as quasi-stochastic…

Optimization and Control · Mathematics 2024-03-26 Caio Kalil Lauand , Sean Meyn

In many sequential decision-making problems one is interested in minimizing an expected cumulative cost while taking into account \emph{risk}, i.e., increased awareness of events of small probability and high consequences. Accordingly, the…

Artificial Intelligence · Computer Science 2017-04-07 Yinlam Chow , Mohammad Ghavamzadeh , Lucas Janson , Marco Pavone

Trajectory optimization under uncertainty underpins a wide range of applications in robotics. However, existing methods are limited in terms of reasoning about sources of epistemic and aleatoric uncertainty, space and time correlations,…

Robotics · Computer Science 2023-09-28 Thomas Lew , Riccardo Bonalli , Marco Pavone

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

Q-learning with neural network function approximation (neural Q-learning for short) is among the most prevalent deep reinforcement learning algorithms. Despite its empirical success, the non-asymptotic convergence rate of neural Q-learning…

Machine Learning · Computer Science 2020-03-05 Pan Xu , Quanquan Gu

We provide a new algorithm for solving Risk Sensitive Partially Observable Markov Decisions Processes, when the risk is modeled by a utility function, and both the state space and the space of observations is finite. This algorithm is based…

Optimization and Control · Mathematics 2022-07-19 Arsham Afsardeir , Andreas Kapetanis , Vaios Laschos , Klaus Obermayer

We propose a multilevel stochastic approximation (MLSA) scheme for the computation of the value-at-risk (VaR) and expected shortfall (ES) of a financial loss, which can only be computed via simulations conditionally on the realisation of…

Computational Finance · Quantitative Finance 2026-04-14 Stéphane Crépey , Noufel Frikha , Azar Louzi

Stochastic versions of proximal methods have gained much attention in statistics and machine learning. These algorithms tend to admit simple, scalable forms, and enjoy numerical stability via implicit updates. In this work, we propose and…

Machine Learning · Statistics 2024-09-09 Haoyu Jiang , Jason Xu

We consider the batch (off-line) policy learning problem in the infinite horizon Markov Decision Process. Motivated by mobile health applications, we focus on learning a policy that maximizes the long-term average reward. We propose a…

Statistics Theory · Mathematics 2022-09-20 Peng Liao , Zhengling Qi , Runzhe Wan , Predrag Klasnja , Susan Murphy

In many applications of Reinforcement Learning (RL), it is critically important that the algorithm performs safely, such that instantaneous hard constraints are satisfied at each step, and unsafe states and actions are avoided. However,…

Machine Learning · Computer Science 2023-02-10 Ming Shi , Yingbin Liang , Ness Shroff

In this paper we present an algorithm to compute risk averse policies in Markov Decision Processes (MDP) when the total cost criterion is used together with the average value at risk (AVaR) metric. Risk averse policies are needed when large…

Optimization and Control · Mathematics 2016-02-17 Stefano Carpin , Yin-Lam Chow , Marco Pavone