Login / Signup

Bias and Extrapolation in Markovian Linear Stochastic Approximation with Constant Stepsizes.

Dongyan HuoYudong ChenQiaomin Xie
Published in: CoRR (2022)
Keyphrases
  • stochastic approximation
  • monte carlo
  • approximate dynamic programming
  • neural network
  • reinforcement learning
  • policy iteration
  • temporal difference learning