Login / Signup

Simultaneous perturbation stochastic approximation of nonsmooth functions.

Vaida BartkuteLeonidas Sakalauskas
Published in: Eur. J. Oper. Res. (2007)
Keyphrases
  • stochastic approximation
  • monte carlo
  • convex functions
  • reinforcement learning
  • least squares
  • markov chain
  • basis functions
  • mathematical programming
  • temporal difference learning