A stochastic maximum principle approach for reinforcement learning with parameterized environment

DOI10.1016/J.JCP.2023.112238arXiv2208.02241OpenAlexW4377101750MaRDI QIDQ6105091

Feng Bao, Jiong-min Yong, Richard Archibald

Publication date: 16 June 2023

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2208.02241

zbMATH Keywords

optimal controlparameter estimationstochastic maximum principleoptimal filteringreinforcement learning

Mathematics Subject Classification ID

Stochastic analysis (60Hxx) Artificial intelligence (68Txx) Probabilistic methods, stochastic differential equations (65Cxx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A random map implementation of implicit filters
• Higher-order implicit strong numerical schemes for stochastic differential equations
• A numerical scheme for BSDEs
• \({\mathcal Q}\)-learning
• An efficient numerical algorithm for solving data driven feedback control problems
• A direct filter method for parameter estimation
• New Kinds of High-Order Multistep Schemes for Coupled Forward Backward Stochastic Differential Equations
• A General Stochastic Maximum Principle for Optimal Control Problems
• An Efficient Gradient Projection Method for Stochastic Optimal Control Problems
• Particle Markov Chain Monte Carlo Methods
• Data assimilation of synthetic data as a novel strategy for predicting disease progression in alopecia areata
• A survey of convergence results on particle filtering methods for practitioners
• A First Order Scheme for Backward Doubly Stochastic Differential Equations

This page was built for publication: A stochastic maximum principle approach for reinforcement learning with parameterized environment