Agrawal, Rishabh, Nathan Dahlin, Rahul Jain, and Ashutosh Nayyar. “Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning”. Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 15 (April 11, 2025): 15311–15319. Accessed May 19, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/33680.