Login / Signup

On the convergence and ODE limit of a two-dimensional stochastic approximation.

Dye-Jyun MaArmand M. Makowski
Published in: IEEE Trans. Autom. Control. (1994)
Keyphrases
  • stochastic approximation
  • monte carlo
  • policy iteration
  • machine learning
  • reinforcement learning
  • ordinary differential equations
  • temporal difference learning
  • optical flow