A Lyapunov approach for stable reinforcement learning

DOI10.1007/S40314-022-01988-YOpenAlexW4293152345MaRDI QIDQ2675741

Julio B. Clempner

Publication date: 26 September 2022

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

Full work available at URL: https://doi.org/10.1007/s40314-022-01988-y

zbMATH Keywords

optimizationMarkov chainsarchitecturereinforcement learningaverage costLyapunov

Mathematics Subject Classification ID

Calculus of variations and optimal control; optimization (49-XX)

Cites Work

• Unnamed Item
• Learning macroscopic parameters in nonlinear multiscale simulations using nonlocal multicontinua upscaling techniques
• Preconditioning Markov chain Monte Carlo method for geomechanical subsidence using multiscale method and machine learning technique
• Toward optimal probabilistic active learning using a Bayesian approach
• Controller exploitation-exploration reinforcement learning architecture for computing near-optimal policies
• Convergence method, properties and computational complexity for Lyapunov games
• Setting Cournot Versus Lyapunov Games Stability Conditions and Equilibrium Point Properties
• 10.1162/jmlr.2003.3.4-5.803

This page was built for publication: A Lyapunov approach for stable reinforcement learning