LI, Songlin; XIAO, Wei; WU, Hao; ZHANG, Xiaodan; AN, Daolong; LÜ, Shuai. State Proficiency-Based Adaptive Fine-Tuning for Offline-to-Online Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 28, p. 23169–23176, 2026. DOI: 10.1609/aaai.v40i28.39484. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39484. Acesso em: 14 may. 2026.