Sample-efficient reinforcement learning using deep Gaussian processes.

Charles W. L. Gadd Markus Heinonen Harri Lähdesmäki Samuel Kaski

Published in: CoRR (2020)

Keyphrases

gaussian processes
reinforcement learning
gaussian process
multi task learning
gaussian process regression
relational reinforcement learning
multitask learning
multi task
human pose estimation
preference learning
learning tasks
covariance function