Learning Invariances for Policy Generalization.

Remi Tachet des Combes Philip Bachman Harm van Seijen

Published in: ICLR (Workshop) (2018)

Keyphrases

learning algorithm
learning systems
learning tasks
online learning
learning process
supervised learning
learning scheme
knowledge acquisition
learning problems
action selection
e learning
active learning
dynamic programming
learning analytics
learning machines
explanation based generalization