Login / Signup

Convergence of Markovian Stochastic Approximation with Discontinuous Dynamics.

Gersende FortEric MoulinesAmandine SchreckMatti Vihola
Published in: SIAM J. Control. Optim. (2016)
Keyphrases
  • stochastic approximation
  • monte carlo
  • policy iteration
  • reinforcement learning
  • dynamical systems
  • convergence rate
  • temporal difference learning
  • theoretical guarantees