Chaotic dynamics and convergence analysis of temporal difference algorithms with bang-bang control

DOI10.1002/oca.2156zbMath1353.68243OpenAlexW1520148289MaRDI QIDQ2800471

No author found.

Publication date: 15 April 2016

Published in: Optimal Control Applications and Methods (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/oca.2156

zbMATH Keywords

rate of convergencetemporal difference learningvalue function approximationpolynomial basis functionsbadly conditioned learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of optimal control and differential games (49N90) Dynamic programming (90C39)

Uses Software

• Approxrl

Cites Work

• Micro-chaotic dynamics due to digital sampling in hybrid systems of Filippov type
• The convergence of \(TD(\lambda)\) for general \(\lambda\)
• On the worst-case analysis of temporal-difference learning algorithms
• 10.1162/153244303768966102
• First-Order System Least Squares for Second-Order Partial Differential Equations: Part II
• An analysis of temporal-difference learning with function approximation
• Optimal chaos control through reinforcement learning
• Temporal Difference Methods for General Projected Equations

This page was built for publication: Chaotic dynamics and convergence analysis of temporal difference algorithms with bang-bang control