Evaluations of the Gap Between Supervised and Reinforcement Lifelong Learning on Robotic Manipulation Tasks
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
Text
Yang et al. "Evaluations of the Gap Between Supervised and Reinforcement Lifelong Learning on Robotic Manipulation Tasks." Conference on Robot Learning, 2021.Markdown
[Yang et al. "Evaluations of the Gap Between Supervised and Reinforcement Lifelong Learning on Robotic Manipulation Tasks." Conference on Robot Learning, 2021.](https://mlanthology.org/corl/2021/yang2021corl-evaluations/)BibTeX
@inproceedings{yang2021corl-evaluations,
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 = {Conference on Robot Learning},
year = {2021},
pages = {547-556},
volume = {164},
url = {https://mlanthology.org/corl/2021/yang2021corl-evaluations/}
}