DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks

Tongzhou Mu, Minghua Liu, Hao Su

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Reward Learning, Multi-stage Task

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose DrS, a novel reward learning approach that learns reusable dense rewards for multi-stage tasks.

Abstract: The success of many RL techniques heavily relies on human-engineered dense rewards, which typically demands substantial domain expertise and extensive trial and error. In our work, we propose **DrS** (**D**ense **r**eward learning from **S**tages), a novel approach for learning *reusable* dense rewards for multi-stage tasks in a data-driven manner. By leveraging the stage structures of the task, DrS learns a high-quality dense reward from sparse rewards and demonstrations if given. The learned rewards can be *reused* in unseen tasks, thus reducing the human effort for reward engineering. Extensive experiments on three physical robot manipulation task families with 1000+ task variants demonstrate that our learned rewards can be reused in unseen tasks, resulting in improved performance and sample efficiency of RL algorithms. The learned rewards even achieve comparable performance to human-engineered rewards on some tasks. See our [project page](https://sites.google.com/view/iclr24drs) for more details.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: reinforcement learning

Submission Number: 4068