Fangzhou Xiong
Encoding primitives generation policy learning for robotic arm to overcome catastrophic forgetting in sequential multi-tasks learning
Xiong, Fangzhou; Liu, Zhiyong; Huang, Kaizhu; Yang, Xu; Qiao, Hong; Hussain, Amir
Authors
Abstract
Continual learning, a widespread ability in people and animals, aims to learn and acquire new knowledge and skills continuously. Catastrophic forgetting usually occurs in continual learning when an agent attempts to learn different tasks sequentially without storing or accessing previous task information. Unfortunately, current learning systems, e.g., neural networks, are prone to deviate the weights learned in previous tasks after training new tasks, leading to catastrophic forgetting, especially in a sequential multi-tasks scenario. To address this problem, in this paper, we propose to overcome catastrophic forgetting with the focus on learning a series of robotic tasks sequentially. Particularly, a novel hierarchical neural network’s framework called Encoding Primitives Generation Policy Learning (E-PGPL) is developed to enable continual learning with two components. By employing a variational autoencoder to project the original state space into a meaningful low-dimensional feature space, representative state primitives could be sampled to help learn corresponding policies for different tasks. In learning a new task, the feature space is required to be close to the previous ones so that previously learned tasks can be protected. Extensive experiments on several simulated robotic tasks demonstrate our method’s efficacy to learn control policies for handling sequentially arriving multi-tasks, delivering improvement substantially over some other continual learning methods, especially for the tasks with more diversity.
Citation
Xiong, F., Liu, Z., Huang, K., Yang, X., Qiao, H., & Hussain, A. (2020). Encoding primitives generation policy learning for robotic arm to overcome catastrophic forgetting in sequential multi-tasks learning. Neural Networks, 129, 163-173. https://doi.org/10.1016/j.neunet.2020.06.003
Journal Article Type | Article |
---|---|
Acceptance Date | Jun 2, 2020 |
Online Publication Date | Jun 5, 2020 |
Publication Date | 2020-09 |
Deposit Date | Jun 10, 2020 |
Journal | Neural Networks |
Print ISSN | 0893-6080 |
Publisher | Elsevier |
Peer Reviewed | Peer Reviewed |
Volume | 129 |
Pages | 163-173 |
DOI | https://doi.org/10.1016/j.neunet.2020.06.003 |
Keywords | Sequential multi-tasks learning, Continual learning, Catastrophic forgetting, Robotics |
Public URL | http://researchrepository.napier.ac.uk/Output/2666951 |
You might also like
Guided Policy Search for Sequential Multitask Learning
(2018)
Journal Article
Learning Latent Features With Infinite Nonnegative Binary Matrix Trifactorization
(2018)
Journal Article
Cross-modality interactive attention network for multispectral pedestrian detection
(2018)
Journal Article
Downloadable Citations
About Edinburgh Napier Research Repository
Administrator e-mail: repository@napier.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search