Login / Signup

Fast LSTD Using Stochastic Approximation: Finite Time Analysis and Application to Traffic Control.

Prashanth L. A.Nathaniel KordaRémi Munos
Published in: ECML/PKDD (2) (2014)
Keyphrases
  • traffic control
  • reinforcement learning
  • stochastic approximation
  • temporal difference
  • function approximation
  • policy iteration
  • least squares
  • markov decision processes
  • multi agent
  • upper bound
  • sufficient conditions