Learning Near Optimal Policies with Low Inherent Bellman Error.

Andrea Zanette Alessandro Lazaric Mykel J. Kochenderfer Emma Brunskill

Published in: ICML (2020)

Keyphrases

learning algorithm
online learning
prior knowledge
unsupervised learning
learning process
supervised learning
learning problems
e learning
active learning
knowledge acquisition
error rate
mobile learning
learning tasks
learning scenarios
learning analytics
provably near optimal