English
Related papers

Related papers: Robust $Q$-learning Algorithm for Markov Decision …

200 papers

We investigate a simple approximation scheme, based on overlapping linear decision rules, for solving data-driven two-stage distributionally robust optimization problems with the type-$\infty$ Wasserstein ambiguity set. Our main result…

Optimization and Control · Mathematics 2020-11-05 Dimitris Bertsimas , Shimrit Shtern , Bradley Sturt

In this paper, we consider the problem of optimization and learning for constrained and multi-objective Markov decision processes, for both discounted rewards and expected average rewards. We formulate the problems as zero-sum games where…

Optimization and Control · Mathematics 2021-03-05 Ather Gattami , Qinbo Bai , Vaneet Agarwal

Training machine learning and statistical models often involves optimizing a data-driven risk criterion. The risk is usually computed with respect to the empirical data distribution, but this may result in poor and unstable out-of-sample…

Machine Learning · Statistics 2024-11-11 Nicola Bariletto , Nhat Ho

This paper studies a discrete-time stochastic control problem with linear quadratic criteria over an infinite-time horizon. We focus on a class of control systems whose system matrices are associated with random parameters involving unknown…

Optimization and Control · Mathematics 2022-01-17 Zhaorong Zhang , Juanjuan Xu , Xun Li

This paper studies data-driven distributionally robust bottleneck combinatorial problems (DRBCP) with stochastic costs, where the probability distribution of the cost vector is contained in a ball of distributions centered at the empirical…

Optimization and Control · Mathematics 2021-02-23 Weijun Xie , Jie Zhang , Shabbir Ahmed

Q-learning is a regression-based approach that is widely used to formalize the development of an optimal dynamic treatment strategy. Finite dimensional working models are typically used to estimate certain nuisance parameters, and…

Methodology · Statistics 2020-03-30 Ashkan Ertefaie , James R. McKay , David Oslin , Robert L. Strawderman

We present a general duality result for Wasserstein distributionally robust optimization that holds for any Kantorovich transport cost, measurable loss function, and nominal probability distribution. Assuming an interchangeability principle…

Optimization and Control · Mathematics 2024-11-26 Luhao Zhang , Jincheng Yang , Rui Gao

Using only retrospective data, we study the problem of predicting treatment effects for the same treatment/policy implemented in a different location or time period. We propose a distributionally robust estimator that minimizes the…

Econometrics · Economics 2026-04-29 Ruonan Xu , Xiye Yang

This paper proposes a novel approach to construct data-driven online solutions to optimization problems (P) subject to a class of distributionally uncertain dynamical systems. The introduced framework allows for the simultaneous learning of…

Systems and Control · Electrical Eng. & Systems 2024-07-23 Dan Li , Dariush Fooladivanda , Sonia Martinez

We develop a stochastic approximation-type algorithm to solve finite state/action, infinite-horizon, risk-aware Markov decision processes. Our algorithm has two loops. The inner loop computes the risk by solving a stochastic saddle-point…

Optimization and Control · Mathematics 2019-12-05 Wenjie Huang , William B. Haskell

Robust reinforcement learning (RL) is to find a policy that optimizes the worst-case performance over an uncertainty set of MDPs. In this paper, we focus on model-free robust RL, where the uncertainty set is defined to be centering at a…

Machine Learning · Computer Science 2021-10-29 Yue Wang , Shaofeng Zou

Reinforcement learning (RL) is a classical tool to solve network control or policy optimization problems in unknown environments. The original Q-learning suffers from performance and complexity challenges across very large networks. Herein,…

Machine Learning · Computer Science 2024-09-02 Talha Bozkus , Urbashi Mitra

Gradient boosting is a sequential ensemble method that fits a new weaker learner to pseudo residuals at each iteration. We propose Wasserstein gradient boosting, a novel extension of gradient boosting that fits a new weak learner to…

Methodology · Statistics 2024-08-30 Takuo Matsubara

We propose a method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before. We apply our method to learning maximum entropy policies, resulting into a new…

Machine Learning · Computer Science 2017-07-25 Tuomas Haarnoja , Haoran Tang , Pieter Abbeel , Sergey Levine

We propose REpresentation-Aware Distributionally Robust Estimation (READ), a novel framework for Wasserstein distributionally robust learning that accounts for predictive representations when guarding against distributional shifts. Unlike…

Methodology · Statistics 2025-09-12 Zitao Wang , Nian Si , Molei Liu

Wasserstein distributionally robust optimization (WDRO) strengthens statistical learning under model uncertainty by minimizing the local worst-case risk within a prescribed ambiguity set. Although WDRO has been extensively studied in…

Machine Learning · Statistics 2025-11-12 Changyu Liu , Yuling Jiao , Junhui Wang , Jian Huang

This paper investigates advantages of using 2-Wasserstein ambiguity sets over 1-Wasserstein sets in two-stage distributionally robust optimization with right-hand side uncertainty. We examine the worst-case distributions within 1- and…

Optimization and Control · Mathematics 2025-01-13 Geunyeong Byeon

Optimal transport is a foundational problem in optimization, that allows to compare probability distributions while taking into account geometric aspects. Its optimal objective value, the Wasserstein distance, provides an important loss…

Machine Learning · Computer Science 2020-02-21 Marin Ballu , Quentin Berthet , Francis Bach

Markov decision processes (MDP) are a well-established model for sequential decision-making in the presence of probabilities. In robust MDP (RMDP), every action is associated with an uncertainty set of probability distributions, modelling…

Artificial Intelligence · Computer Science 2024-12-16 Tobias Meggendorfer , Maximilian Weininger , Patrick Wienhöft

Soft Q-learning is a variation of Q-learning designed to solve entropy regularized Markov decision problems where an agent aims to maximize the entropy regularized value function. Despite its empirical success, there have been limited…

Machine Learning · Computer Science 2024-09-06 Narim Jeong , Donghwan Lee
‹ Prev 1 8 9 10 Next ›