REPAINT: Knowledge Transfer in Deep Reinforcement Learning

Accelerating learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and target tasks is low. This work proposes REPresentation And INstance Transfer (REPAINT) a...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-05
Main Authors: Yunzhe Tao, Genc, Sahika, Chung, Jonathan, Sun, Tao, Mallya, Sunil
Format: Article
Language:English
Subjects:
Algorithms
Deep learning
Entropy (Information theory)
Knowledge management
Machine learning
Representations
Task complexity
Teachers
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accelerating learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and target tasks is low. This work proposes REPresentation And INstance Transfer (REPAINT) algorithm for knowledge transfer in deep reinforcement learning. REPAINT not only transfers the representation of a pre-trained teacher policy in the on-policy learning, but also uses an advantage-based experience selection approach to transfer useful samples collected following the teacher policy in the off-policy learning. Our experimental results on several benchmark tasks show that REPAINT significantly reduces the total training time in generic cases of task similarity. In particular, when the source tasks are dissimilar to, or sub-tasks of, the target tasks, REPAINT outperforms other baselines in both training-time reduction and asymptotic performance of return scores.
ISSN:2331-8422