Evaluations of the Gap between Supervised and Reinforcement Lifelong Learning on Robotic Manipulation Tasks

Fan Yang, Chao Yang, Huaping Liu, Fuchun Sun
Proceedings of the 5th Conference on Robot Learning, PMLR 164:547-556, 2022.

Abstract

Overcoming catastrophic forgetting is of great importance for deep learning and robotics. Recent lifelong learning research has great advances in supervised learning. However, little work focuses on reinforcement learning(RL). We focus on evaluating the performances of state-of-the-art lifelong learning algorithms on robotic reinforcement learning tasks. We mainly focus on the properties of overcoming catastrophic forgetting for these algorithms. We summarize the pros and cons for each category of lifelong learning algorithms when applied in RL scenarios. We propose a framework to modify supervised lifelong learning algorithms to be compatible with RL. We also develop a manipulation benchmark task set for our evaluations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v164-yang22a, title = {Evaluations of the Gap between Supervised and Reinforcement Lifelong Learning on Robotic Manipulation Tasks}, author = {Yang, Fan and Yang, Chao and Liu, Huaping and Sun, Fuchun}, booktitle = {Proceedings of the 5th Conference on Robot Learning}, pages = {547--556}, year = {2022}, editor = {Faust, Aleksandra and Hsu, David and Neumann, Gerhard}, volume = {164}, series = {Proceedings of Machine Learning Research}, month = {08--11 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v164/yang22a/yang22a.pdf}, url = {https://proceedings.mlr.press/v164/yang22a.html}, abstract = {Overcoming catastrophic forgetting is of great importance for deep learning and robotics. Recent lifelong learning research has great advances in supervised learning. However, little work focuses on reinforcement learning(RL). We focus on evaluating the performances of state-of-the-art lifelong learning algorithms on robotic reinforcement learning tasks. We mainly focus on the properties of overcoming catastrophic forgetting for these algorithms. We summarize the pros and cons for each category of lifelong learning algorithms when applied in RL scenarios. We propose a framework to modify supervised lifelong learning algorithms to be compatible with RL. We also develop a manipulation benchmark task set for our evaluations.} }
Endnote
%0 Conference Paper %T Evaluations of the Gap between Supervised and Reinforcement Lifelong Learning on Robotic Manipulation Tasks %A Fan Yang %A Chao Yang %A Huaping Liu %A Fuchun Sun %B Proceedings of the 5th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2022 %E Aleksandra Faust %E David Hsu %E Gerhard Neumann %F pmlr-v164-yang22a %I PMLR %P 547--556 %U https://proceedings.mlr.press/v164/yang22a.html %V 164 %X Overcoming catastrophic forgetting is of great importance for deep learning and robotics. Recent lifelong learning research has great advances in supervised learning. However, little work focuses on reinforcement learning(RL). We focus on evaluating the performances of state-of-the-art lifelong learning algorithms on robotic reinforcement learning tasks. We mainly focus on the properties of overcoming catastrophic forgetting for these algorithms. We summarize the pros and cons for each category of lifelong learning algorithms when applied in RL scenarios. We propose a framework to modify supervised lifelong learning algorithms to be compatible with RL. We also develop a manipulation benchmark task set for our evaluations.
APA
Yang, F., Yang, C., Liu, H. & Sun, F.. (2022). Evaluations of the Gap between Supervised and Reinforcement Lifelong Learning on Robotic Manipulation Tasks. Proceedings of the 5th Conference on Robot Learning, in Proceedings of Machine Learning Research 164:547-556 Available from https://proceedings.mlr.press/v164/yang22a.html.

Related Material