Learning Diverse Sub-Policies via a Task-Agnostic Regularization on Action Distributions.

Liangyu Huo Zulin Wang Mai Xu Yuhang Song

Published in: ICASSP (2020)

Keyphrases

learning algorithm
learning process
learning tasks
active learning
learning systems
reinforcement learning
supervised learning
mobile learning
prior knowledge
probabilistic model
probability distribution
multi class
knowledge acquisition
learning problems
action models
multi view learning