English
Related papers

Related papers: Operator Splitting Value Iteration

200 papers

In big data analysis, a simple task such as linear regression can become very challenging as the variable dimension $p$ grows. As a result, variable screening is inevitable in many scientific studies. In recent years, randomized algorithms…

Methodology · Statistics 2019-02-13 Yu-Hsiang Cheng , Tzee-Ming Huang , Su-Yun Huang

The problem of Offline Policy Evaluation (OPE) in Reinforcement Learning (RL) is a critical step towards applying RL in real-life applications. Existing work on OPE mostly focus on evaluating a fixed target policy $\pi$, which does not…

Machine Learning · Computer Science 2020-12-02 Ming Yin , Yu Bai , Yu-Xiang Wang

Modern artificial intelligence relies on networks of agents that collect data, process information, and exchange it with neighbors to collaboratively solve optimization and learning problems. This article introduces a novel distributed…

Optimization and Control · Mathematics 2026-01-15 Diego Deplano , Nicola Bastianello , Mauro Franceschelli , Karl H. Johansson

In reinforcement learning (RL), offline learning decoupled learning from data collection and is useful in dealing with exploration-exploitation tradeoff and enables data reuse in many applications. In this work, we study two offline…

Machine Learning · Computer Science 2022-02-08 Jing Dong , Xin T. Tong

We study offline Reinforcement Learning in large infinite-horizon discounted Markov Decision Processes (MDPs) when the reward and transition models are linearly realizable under a known feature map. Starting from the classic linear-program…

Machine Learning · Computer Science 2024-05-24 Gergely Neu , Nneka Okolo

Model-based offline reinforcement learning trains policies using pre-collected datasets and learned environment models, eliminating the need for direct real-world environment interaction. However, this paradigm is inherently challenged by…

Machine Learning · Computer Science 2025-10-28 Wang Luo , Haoran Li , Zicheng Zhang , Congying Han , Chi Zhou , Jiayu Lv , Tiande Guo

Mixed-integer optimisation problems can be computationally challenging. Here, we introduce and analyse two efficient algorithms with a specific sequential design that are aimed at dealing with sampled problems within this class. At each…

Optimization and Control · Mathematics 2023-03-07 Mohammadreza Chamanbaz , Roland Bouffanais

Existing operator learning methods rely on supervised training with high-fidelity simulation data, introducing significant computational cost. In this work, we propose the deep Onsager operator learning (DOOL) method, a novel unsupervised…

Machine Learning · Computer Science 2025-08-12 Zhipeng Chang , Zhenye Wen , Xiaofei Zhao

Imitation learning, followed by reinforcement learning algorithms, is a promising paradigm to solve complex control tasks sample-efficiently. However, learning from demonstrations often suffers from the covariate shift problem, which…

Machine Learning · Computer Science 2019-10-14 Yuping Luo , Huazhe Xu , Tengyu Ma

We introduce the Optimizing a Discrete Loss (ODIL) framework for the numerical solution of Partial Differential Equations (PDE) using machine learning tools. The framework formulates numerical methods as a minimization of discrete residuals…

Numerical Analysis · Mathematics 2024-01-23 Petr Karnakov , Sergey Litvinov , Petros Koumoutsakos

We present a different view on stochastic optimization, which goes back to the splitting schemes for approximate solutions of ODE. In this work, we provide a connection between stochastic gradient descent approach and first-order splitting…

Machine Learning · Statistics 2020-04-21 Daniil Merkulov , Ivan Oseledets

We consider the Inverse Optimal Stopping (IOS) problem where, based on stopped expert trajectories, one aims to recover the optimal stopping region through the continuation and stopping gain functions approximation. The uniqueness of the…

Machine Learning · Statistics 2025-11-03 Anna Kuchko

Reinforcement learning (RL) allows an agent interacting sequentially with an environment to maximize its long-term expected return. In the distributional RL (DistrRL) paradigm, the agent goes beyond the limit of the expected value, to…

Machine Learning · Computer Science 2023-05-01 Mastane Achab , Reda Alami , Yasser Abdelaziz Dahou Djilali , Kirill Fedyanin , Eric Moulines

Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious. However, prior IRL algorithms use on-policy transitions, which require intensive sampling from the current policy for stable and…

Machine Learning · Computer Science 2022-05-24 Hana Hoshino , Kei Ota , Asako Kanezaki , Rio Yokota

Numerous Optimization Algorithms have a time-varying update rule thanks to, for instance, a changing step size, momentum parameter or, Hessian approximation. In this paper, we apply unrolled or automatic differentiation to a time-varying…

Optimization and Control · Mathematics 2024-10-28 Sheheryar Mehmood , Peter Ochs

We study how group symmetry helps improve data efficiency and generalization for end-to-end differentiable planning algorithms when symmetry appears in decision-making tasks. Motivated by equivariant convolution networks, we treat the path…

Machine Learning · Computer Science 2023-05-02 Linfeng Zhao , Xupeng Zhu , Lingzhi Kong , Robin Walters , Lawson L. S. Wong

This note re-visits the rolling-horizon control approach to the problem of a Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished from the classical value-iteration approach, we develop an…

Optimization and Control · Mathematics 2022-06-07 Hyeong Soo Chang

We consider approximate dynamic programming in $\gamma$-discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first contribution is a new variant of Approximate Policy…

Machine Learning · Computer Science 2022-10-31 Gellért Weisz , András György , Tadashi Kozuno , Csaba Szepesvári

We propose an inexact variable-metric proximal point algorithm to accelerate gradient-based optimization algorithms. The proposed scheme, called QNing can be notably applied to incremental first-order methods such as the stochastic…

Machine Learning · Statistics 2019-01-30 Hongzhou Lin , Julien Mairal , Zaid Harchaoui

In this paper we propose an on-line policy iteration (PI) algorithm for finite-state infinite horizon discounted dynamic programming, whereby the policy improvement operation is done on-line, only for the states that are encountered during…

Optimization and Control · Mathematics 2021-06-03 Dimitri Bertsekas
‹ Prev 1 8 9 10 Next ›