Login / Signup

A counterexample to Dvoretzky's stochastic approximation theorem (Corresp.).

Charles T. WolvertonJ. T. Rawgen
Published in: IEEE Trans. Inf. Theory (1968)
Keyphrases
  • stochastic approximation
  • monte carlo
  • multi start
  • model checking
  • temporal difference learning
  • reinforcement learning
  • policy iteration