DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks

arXiv:2404.16779v1 Announce Type: new
Abstract: The success of many RL techniques heavily relies on human-engineered dense rewards, which typically demand substantial domain expertise and extensive trial and error. In our work, we propose DrS (Dense reward learning from Stages), 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 …

arxiv cs.ai cs.lg cs.ro stage tasks type