CoinDICE: Off-Policy Confidence Interval Estimation.

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

Published in: CoRR (2020)

Keyphrases

interval estimation
collaborative filtering
markov decision processes
high confidence
confidence level
artificial intelligence
real time
machine learning
social networks
special case
dynamic programming
confidence measure
confidence measures
confidence values