Convergence results for an averaged LQR problem with applications to reinforcement learning

DOI10.1007/s00498-021-00294-yzbMath1475.49041arXiv2011.03447OpenAlexW3182492475MaRDI QIDQ2236442

Andrea Pesare, Michele Palladino, Maurizio Falcone

Publication date: 25 October 2021

Published in: MCSS. Mathematics of Control, Signals, and Systems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.03447

zbMATH Keywords

optimal controlconvergencelinear quadratic regulatorreinforcement learningaveraged controlmodel-based RL

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Linear-quadratic optimal control problems (49N10)

Related Items (2)

A new algorithm for the LQR problem with partially unknown dynamics ⋮ Optimal control of ensembles of dynamical systems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• From averaged to simultaneous controllability
• Necessary conditions for adverse control problems expressed by relaxed derivatives
• A study of reinfrocement learning in the continuous case by the means of viscosity solutions
• A model for system uncertainty in reinforcement learning
• Necessary optimality conditions for average cost minimization problems
• Averaged control
• 18.—Linear-quadratic Optimal Control
• Optimal Transport
• Optimal control

This page was built for publication: Convergence results for an averaged LQR problem with applications to reinforcement learning