Umbrella reinforcement learning -- computationally efficient tool for hard non-linear problems

DOI10.1016/J.CNSNS.2024.108583MaRDI QIDQ7009256zbMATH OpenFDO

Authors Egor E. Nuzhin, Nikolay V. Brilliantov

Publication date 20 March 2025

Published in Communications in Nonlinear Science and Numerical Simulation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.CNSNS.2024.108583

zbMATH Keywords

dynamic programmingpolicy gradientreinforcement learningRLumbrella sampling

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07) Dynamic programming (90C39)

Cites work

• \({\mathcal Q}\)-learning
• A survey of inverse reinforcement learning: challenges, methods and progress
• Continuous-time Markov decision processes. Theory and applications
• Deep reinforcement learning. Fundamentals, research and applications
• scientific article; zbMATH DE number 3148886 (Why is no real title available?)
• scientific article; zbMATH DE number 1082719 (Why is no real title available?)
• Reinforcement learning. An introduction
• Temperature-and-density-scaling Monte Carlo: methodology and the canonical thermodynamics of Lennard-Jonesium
• The entropy of Markov trajectories

Cited in

(1)

• An effective control of large systems of active particles: an application to evacuation problem

This page was built for publication: Umbrella reinforcement learning -- computationally efficient tool for hard non-linear problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7009256)