Li, Songlin, Wei Xiao, Hao Wu, Xiaodan Zhang, Daolong An, and Shuai Lü. 2026. “State Proficiency-Based Adaptive Fine-Tuning for Offline-to-Online Reinforcement Learning”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (28):23169-76. https://doi.org/10.1609/aaai.v40i28.39484.