Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy

Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy

In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from simpler tasks, and faster by adapting the complexity of the ac...

Full description

Bibliographic Details
Main Authors: Nicolas Duminy, Sao Mai Nguyen, Junshuai Zhu, Dominique Duhaut, Jerome Kerdreux
Format: Article
Language:English
Published: MDPI AG 2021-01-01
Series:Applied Sciences
Subjects:
curriculum learning
continual learning
hierarchical reinforcement learning
interactive reinforcement learning
imitation learning
multi-task learning
Online Access:https://www.mdpi.com/2076-3417/11/3/975

Internet

https://www.mdpi.com/2076-3417/11/3/975

Similar Items