On the worst-case analysis of temporal-difference learning algorithms

DOI10.1007/BF00114725zbMath0843.68093OpenAlexW1976578332MaRDI QIDQ1911342

Manfred K. Warmuth, Robert E. Schapire

Publication date: 21 April 1996

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf00114725

zbMATH Keywords

learning algorithmsSutton's method of temporal differences

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (3)

Chaotic dynamics and convergence analysis of temporal difference algorithms with bang-bang control ⋮ Scalable estimation strategies based on stochastic approximations: classical results and new insights ⋮ A Finite Time Analysis of Temporal Difference Learning with Linear Function Approximation

Cites Work

• Unnamed Item
• The convergence of \(TD(\lambda)\) for general \(\lambda\)
• Matrix Analysis
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms

This page was built for publication: On the worst-case analysis of temporal-difference learning algorithms