Feature-based methods for large scale dynamic programming

DOI10.1007/BF00114724zbMath0843.68092MaRDI QIDQ1911341

John N. Tsitsiklis, Benjamin van Roy

Publication date: 21 April 1996

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

zbMATH Keywords

dynamic programming

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (9)

Approximate policy iteration: a survey and some new methods ⋮ A review of stochastic algorithms with continuous value function approximation and some new approximate policy iteration algorithms for multidimensional continuous applications ⋮ Dynamic programming approximation algorithms for the capacitated lot-sizing problem ⋮ Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty ⋮ Shape constraints in economics and operations research ⋮ The actor-critic algorithm as multi-time-scale stochastic approximation. ⋮ Data-driven models for capacity allocation of inpatient beds in a Chinese public hospital ⋮ The Benefits of State Aggregation with Extreme-Point Weighting for Assemble-to-Order Systems ⋮ Single sample path-based optimization of Markov chains

Cites Work

• Unnamed Item
• Unnamed Item
• Generalized polynomial approximations in Markovian decision processes
• Asynchronous stochastic approximation and Q-learning
• Practical issues in temporal difference learning
• \({\mathcal Q}\)-learning
• The convergence of \(TD(\lambda)\) for general \(\lambda\)
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• Functional Approximations and Dynamic Programming
• Adaptive aggregation methods for infinite horizon dynamic programming
• Approximations of Dynamic Programs, I

This page was built for publication: Feature-based methods for large scale dynamic programming