Learning Near Optimal Policies with Low Inherent Bellman Error.

Andrea Zanette Alessandro Lazaric Mykel J. Kochenderfer Emma Brunskill

Published in: CoRR (2020)

Keyphrases

learning process
learning tasks
learning algorithm
supervised learning
knowledge acquisition
learning systems
learning problems
learning environment
online learning
incremental learning
active learning
error rate
predictive state representations