Login / Signup
Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning.
Gregory Farquhar
Shimon Whiteson
Jakob N. Foerster
Published in:
CoRR (2019)
Keyphrases
</>
reinforcement learning
score function
low variance
machine learning
learning algorithm
computer vision
variance reduction
bias variance decomposition