@inproceedings{ lei2024unio, title={Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization}, author={Kun LEI and Zhengmao He and Chenhao Lu and Kaizhe Hu and Yang Gao and Huazhe Xu}, booktitle={The Twelfth International Conference on Learning Representations}, year={2024}, url={https://openreview.net/forum?id=tbFBh3LMKi} }