metadata
title: RISE RL
emoji: 🧠
colorFrom: yellow
colorTo: indigo
sdk: static
pinned: false
license: apache-2.0
short_description: Rubric-Informed Selective Exploration
RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning
Official project page for RISE-RL.
- Paper: https://arxiv.org/abs/2608.09123
- PDF: https://arxiv.org/pdf/2608.09123
- Project Page: https://huggingface.co/spaces/houkunkun/RISE-RL
Authors
Jinkun Hou, Zhuo Liu, Huimin Ren, Hongsheng Xin, Pan Zhou, Kun Zhan
Abstract
RISE-RL is a rubric-informed selective exploration method for open-ended reinforcement learning. It uses repeatedly missed rubric criteria to elicit privileged trajectories that are difficult to discover through unguided exploration alone.
For the complete abstract and experimental results, see our paper:
https://arxiv.org/abs/2608.09123
Citation
@article{hou2026riserl,
title = {RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning},
author = {Hou, Jinkun and Liu, Zhuo and Ren, Huimin and Xin, Hongsheng and Zhou, Pan and Zhan, Kun},
journal = {arXiv preprint arXiv:2608.09123},
year = {2026}
}