Fitted Q-iteration by functional networks for control problems

DOI10.1016/J.APM.2016.05.049MaRDI QIDQ2293779zbMATH OpenOpenAlexWikidataFDO

Authors Matteo Gaeta, Vincenzo Loia, Sergio Miranda, S. Tomasiello

Publication date 5 February 2020

Published in Applied Mathematical Modelling (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.apm.2016.05.049

zbMATH Keywords

control problemsconvergence analysisfunctional networksnumerical methodsQ-function

Mathematics Subject Classification ID

Numerical aspects of recurrence relations (65Q30) Learning and adaptive systems in artificial intelligence (68T05) Adaptive control/observation systems (93C40) Automated systems (robots, etc.) in control theory (93C85)

Recommendations

• The functional link net and learning optimal control
• 10.1162/1532443041827907
• Approximate dynamic programming with a fuzzy parameterization
• Finite-time bounds for fitted value iteration
• Approximating networks and extended Ritz method for the solution of functional optimization problems

Cites work

• \({\mathcal Q}\)-learning
• A functional network to predict fresh and hardened properties of self-compacting concretes
• Extremely randomized trees
• Functional equations in applied sciences
• scientific article; zbMATH DE number 5957269 (Why is no real title available?)
• scientific article; zbMATH DE number 274379 (Why is no real title available?)
• Kernel-based reinforcement learning
• Learning algorithms for Markov decision processes with average cost
• Pattern recognition using neural and functional networks
• Tidal level forecasting using functional and sequential learning neural networks
• Working with differential, functional and difference equations using functional networks

Cited in

(1)

• Optimal tracking control of nonlinear batch processes with unknown dynamics using two-dimensional off-policy interleaved Q-learning algorithm

Describes a project that uses

Uses Software

• Approxrl

This page was built for publication: Fitted Q-iteration by functional networks for control problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2293779)