Efficient Multi-Task and Transfer Reinforcement Learning With Parameter-Compositional Framework

Lingfeng Sun; Haichao Zhang; Wei Xu; Masayoshi Tomizuka

RA-L 202313 citations

Efficient Multi-Task and Transfer Reinforcement Learning With Parameter-Compositional Framework

Lingfeng Sun, Haichao Zhang, Wei Xu, Masayoshi Tomizuka

Abstract

In this work, we investigate the potential of improving multi-task training and also leveraging it for transferring in the reinforcement learning setting. We identify several challenges towards this goal and propose a transferring approach with a parameter-compositional formulation. We investigate ways to improve the training of multi-task reinforcement learning which serves as the foundation for transferring. Then we conduct a number of transferring experiments on various manipulation tasks. Experimental results demonstrate that the proposed approach can have improved performance in the multi-task training stage, and further show effective transferring in terms of both sample efficiency and performance.

BibTeX

@inproceedings{ral2023_efficientmultita,
  title = {Efficient Multi-Task and Transfer Reinforcement Learning With Parameter-Compositional Framework},
  author = {Lingfeng Sun and Haichao Zhang and Wei Xu and Masayoshi Tomizuka},
  booktitle = {RA-L 2023},
  year = {2023}
}