@article{https://resolver.caltech.edu/CaltechAUTHORS:20220714-212437915,
    title = "Langevin Monte Carlo for Contextual Bandits",
    journal = "Proceedings of Machine Learning Research",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20220714-212437915",
    id = "record",
    issn = "2640-3498",
    doi = "10.48550/arXiv.arXiv.2206.11254",
    volume = "162"
}


@article{https://resolver.caltech.edu/CaltechAUTHORS:20210907-195235166,
    title = "Convergence Analysis of Gradient-Based Learning in Continuous Games",
    journal = "Proceedings of Machine Learning Research",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210907-195235166",
    id = "record",
    issn = "2640-3498",
    volume = "115"
}


@article{https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215724,
    title = "Inverse Risk-Sensitive Reinforcement Learning",
    journal = "IEEE Transactions on Automatic Control",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215724",
    id = "record",
    issn = "0018-9286",
    doi = "10.1109/TAC.2019.2926674",
    volume = "65"
}


@article{https://resolver.caltech.edu/CaltechAUTHORS:20210907-200115513,
    title = "On Gradient-Based Learning in Continuous Games",
    journal = "SIAM Journal on Mathematics of Data Science",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210907-200115513",
    id = "record",
    issn = "2577-0187",
    doi = "10.1137/18m1231298",
    volume = "2"
}