Login / Signup

Strong consistency of parameter estimates in direct self-tuning control algorithms based on stochastic approximation.

Miloje S. RadenkovicSrdjan S. Stankovic
Published in: Autom. (1990)
Keyphrases
  • stochastic approximation
  • policy iteration
  • parameter estimates
  • learning algorithm
  • control method
  • computer vision
  • reinforcement learning
  • least squares
  • worst case
  • control strategy