FP-IRL: Fokker–Planck inverse reinforcement learning — A physics-constrained approach to Markov decision processes
Authors:
- Chengyang HuangCHChengyang Huang
- Siddhartha SrivastavaSSSiddhartha Srivastava
- Kenneth K.Y. HoKHKenneth K.Y. Ho
- Kathryn E. LukerKLKathryn E. Luker
- Gary D. LukerGLGary D. Luker
- Xun HuanXHXun Huan
- Krishna GarikipatiKGKrishna Garikipati
- 30 April 2026
- journal article
- Published by Elsevier in Computer Methods in Applied Mechanics and Engineering
- Vol. 458
Abstract
No abstract availableAll Related Versions
Funding Information
- W. M. Keck Foundation
This publication has 12 references indexed in Scilit:
- A survey of inverse reinforcement learningArtificial Intelligence Review, 2022
- A survey of inverse reinforcement learning: Challenges, methods and progressArtificial Intelligence, 2021
- Variational system identification of the partial differential equations governing microstructure evolution in materials: Inference over sparse and spatially unrelated dataComputer Methods in Applied Mechanics and Engineering, 2021
- Variational system identification of the partial differential equations governing the physics of pattern-formation: Inference under varying fidelity and noiseComputer Methods in Applied Mechanics and Engineering, 2019
- Perspectives on the mathematics of biological patterning and morphogenesisJournal of the Mechanics and Physics of Solids, 2017
- Modeling crowd dynamics by the mean-field limit approachMathematical and Computer Modelling, 2010
- Free energy and the Fokker-Planck equationPhysica D: Nonlinear Phenomena, 1997
- The geometry of optimal transportationActa Mathematica, 1996
- On Brownian motion, Boltzmann’s equation, and the Fokker-Planck equationQuarterly of Applied Mathematics, 1952
- On the Theory of Dynamic ProgrammingProceedings of the National Academy of Sciences, 1952