@other{https://resolver.caltech.edu/CaltechAUTHORS:20190410-120658254, title = "Multi-dueling Bandits with Dependent Arms", url = "https://resolver.caltech.edu/CaltechAUTHORS:20190410-120658254", id = "record", doi = "10.48550/arXiv.1705.00253" } @other{https://resolver.caltech.edu/CaltechAUTHORS:20190410-120640737, title = "Bellman Gradient Iteration for Inverse Reinforcement Learning", url = "https://resolver.caltech.edu/CaltechAUTHORS:20190410-120640737", id = "record", doi = "10.48550/arXiv.1707.07767" } @other{https://resolver.caltech.edu/CaltechAUTHORS:20190205-133559444, title = "Correlational Dueling Bandits with Application to Clinical Treatment in Large Decision Spaces", url = "https://resolver.caltech.edu/CaltechAUTHORS:20190205-133559444", id = "record", doi = "10.48550/arXiv.1707.02375" }