Reinforcement Learning based Sequential Batch-sampling for Bayesian Optimal Experimental Design.

Yonatan Ashenafi Piyush Pandita Sayan Ghosh

Published in: CoRR (2021)

Keyphrases

experimental design
reinforcement learning
stochastic dynamic programming
sample size
empirical studies
approximate dynamic programming
active learning
experimental designs
optimal solution
data sets
training data
worst case
learning experience
random sampling
control policy