Control randomisation approach for policy gradient and application to reinforcement learning in optimal switching

DOI10.1007/s00245-024-10207-5MaRDI QIDQ6657507

Xavier Warin, Huyên Pham, Robert Denkert

Publication date: 6 January 2025

Published in: Applied Mathematics and Optimization (Search for Journal in Brave)

zbMATH Keywords

actor-critic algorithmsoptimal switchingpolicy gradientcontrol randomizationreinforcement learning in continuous time

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Model systems in control theory (93Cxx) Controllability, observability, and system structure (93Bxx)

Cites Work

• Unnamed Item
• Representation of non-Markovian optimal stopping problems by constrained BSDEs with a single jump
• Valuation of power plants by utility indifference and numerical computation
• Backward SDEs with constrained jumps and quasi-variational inequalities
• Probabilistic representation and approximation for coupled systems of variational inequalities
• Feynman-Kac representation for Hamilton-Jacobi-Bellman IPDE
• Randomized and backward SDE representation for optimal control of non-Markovian SDEs
• Monte-Carlo Valuation of American Options: Facts and New Algorithms to Improve Existing Methods
• Valuation of energy storage: an optimal switching approach
• A stochastic target formulation for optimal switching problems in finite horizon
• Multivariate point processes: predictable projection, Radon-Nikodym derivatives, representation of martingales
• On the Starting and Stopping Problem: Application in Reversible Investments
• Reservoir optimization and Machine Learning methods
• Randomized Optimal Stopping Problem in Continuous time and Reinforcement Learning Algorithm

This page was built for publication: Control randomisation approach for policy gradient and application to reinforcement learning in optimal switching