Oh, Min-hwan, and Garud Iyengar. “Multinomial Logit Contextual Bandits: Provable Optimality and Practicality”. Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 10 (May 18, 2021): 9205-9213. Accessed March 28, 2024. https://ojs.aaai.org/index.php/AAAI/article/view/17111.