Agrawal, Rishabh, Nathan Dahlin, Rahul Jain, and Ashutosh Nayyar. 2025. “Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning”. Proceedings of the AAAI Conference on Artificial Intelligence 39 (15):15311-19. https://doi.org/10.1609/aaai.v39i15.33680.