Online Multi-Task Learning for Policy Gradient Methods.

Haitham Bou-Ammar Eric Eaton Paul Ruvolo Matthew E. Taylor

Published in: ICML (2014)

Keyphrases

multi task learning
multi task
multiple tasks
learning tasks
gaussian processes
learning problems
multitask learning
policy gradient methods
high order
learning models
neural network
learning algorithm
transfer learning
learning experience
theoretical analysis
higher order
natural actor critic