Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task Division.

Dafni Antotsiou Carlo Ciliberto Tae-Kyun Kim

Published in: CoRR (2022)

Keyphrases

multi task
imitation learning
maximum margin
multi task learning
learning tasks
feature selection
gaussian processes
learning problems
robotic systems
multi class
transfer learning
information gain
humanoid robot
reinforcement learning
optimal policy
multiple kernel learning
data sets