Stable Function Approximation in Dynamic Programming

This publication has 14 references indexed in Scilit:

• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
  Neural Computation, 1994
• An upper bound on the loss from approximate optimal-value functions
  Machine Learning, 1994
• Asynchronous stochastic approximation and Q-learning
  Machine Learning, 1994
• The convergence of TD(?) for general ?
  Machine Learning, 1992
• Self-improving reactive agents based on reinforcement learning, planning and teaching
  Machine Learning, 1992
• Q-learning
  Machine Learning, 1992
• Learning to predict by the methods of temporal differences
  Machine Learning, 1988
• An adaptive optimal controller for discrete-time Markov environments
  Information and Control, 1977
• Discounted Dynamic Programming
  The Annals of Mathematical Statistics, 1965
• Functional Approximations and Dynamic Programming
  Mathematical Tables and Other Aids to Computation, 1959