CoinDICE: Off-Policy Confidence Interval Estimation.

Bo Dai Ofir Nachum Yinlam Chow Lihong Li Csaba Szepesvári Dale Schuurmans

Published in: NeurIPS (2020)

Keyphrases

interval estimation
collaborative filtering
markov decision processes
high confidence
confidence level
confidence values
confidence measure
neural network
machine learning
database systems
training data
optimal solution
ground truth
confidence levels