Constrained representation learning for recurrent policy optimisation under uncertainty.

Viet-Hung Dang Ngo Anh Vien TaeChoong Chung

Published in: Adapt. Behav. (2021)

Keyphrases

learning process
learning algorithm
knowledge acquisition
learning systems
reinforcement learning
genetic algorithm
multiscale
unsupervised learning
learning rules
partially observable
inverse reinforcement learning