Multi-agent reinforcement learning aided sampling algorithms for a class of multiscale inverse problems

DOI10.1007/S10915-023-02279-2MaRDI QIDQ6164983zbMATH OpenFDO

Authors Eric T. Chung, Wing Tat Leung, Sai-Mang Pun, Zecheng Zhang

Publication date 28 July 2023

Published in Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10915-023-02279-2

zbMATH Keywords

inverse problemMCMCmultiscalereinforcement learning

Mathematics Subject Classification ID

Parametric inference (62Fxx) Probabilistic methods, stochastic differential equations (65Cxx) Numerical methods for partial differential equations, boundary value problems (65Nxx)

Cites work

• A Bayesian approach to multiscale inverse problems using the sequential Monte Carlo method
• A Bayesian approach to multiscale inverse problems with on-the-fly scale determination
• A multi-resolution, non-parametric, Bayesian framework for identification of spatially-varying model parameters
• Adaptive multiscale model reduction with generalized multiscale finite element methods
• B-DeepONet: an enhanced Bayesian deeponet for solving noisy parametric PDEs using accelerated replica exchange SGLD
• Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems
• Computational multiscale method for parabolic wave approximations in heterogeneous media
• Computational multiscale methods for quasi-gas dynamic equations
• Constraint energy minimizing generalized multiscale finite element method
• Deep reinforcement learning for the control of conjugate heat transfer
• Equation of state calculations by fast computing machines
• Estimating posterior quantity of interest expectations in a multilevel scalable framework
• Generalized multiscale finite element methods (GMsFEM)
• Generalized multiscale inversion for heterogeneous problems
• Monte Carlo sampling methods using Markov chains and their applications
• Multilevel Markov Chain Monte Carlo
• Multilevel sequential Monte Carlo for Bayesian inverse problems
• Preconditioning Markov Chain Monte Carlo Simulations Using Coarse-Scale Models
• Reinforcement learning. An introduction
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Solution of inverse problems with limited forward solver evaluations: a Bayesian perspective

Cited in

(3)

• Tensor neural network-based machine learning method for elliptic multiscale problems
• Multicontinuum inversion for multiscale problems
• An agent-oriented hierarchic strategy for solving inverse problems

This page was built for publication: Multi-agent reinforcement learning aided sampling algorithms for a class of multiscale inverse problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6164983)