Login / Signup

Variance Reduction for Score Functions Using Optimal Baselines.

Ronan KeaneHuaizhu Oliver Gao
Published in: CoRR (2022)
Keyphrases
  • variance reduction
  • monte carlo
  • gradient estimation
  • dynamic programming
  • sample size
  • optimal solution
  • closed form
  • bias variance decomposition
  • quasi monte carlo
  • reinforcement learning
  • random numbers