@other{https://resolver.caltech.edu/CaltechAUTHORS:20230316-204025426,
    title = "Convergent First-Order Methods for Bi-level Optimization and Stackelberg Games",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20230316-204025426",
    id = "record"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20230316-204015123,
    title = "A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20230316-204015123",
    id = "record"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20230316-204028845,
    title = "Algorithmic Collective Action in Machine Learning",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20230316-204028845",
    id = "record"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221219-234102223,
    title = "Synthesizing Reactive Test Environments for Autonomous Systems: Testing Reach-Avoid Specifications with Multi-Commodity Flows",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221219-234102223",
    id = "record",
    doi = "10.48550/arXiv.2210.10304"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20221220-221907545,
    title = "A Note on Zeroth-Order Optimization on the Simplex",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20221220-221907545",
    id = "record",
    doi = "10.48550/arXiv.2208.01185"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20220715-171641949,
    title = "Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20220715-171641949",
    id = "record",
    doi = "10.48550/arXiv.arXiv.2206.02344"
}


@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"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20210903-213656891,
    title = "Convergence Analysis of Gradient-Based Learning with Non-Uniform Learning Rates in Non-Cooperative Multi-Agent Settings",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-213656891",
    id = "record",
    doi = "10.48550/arXiv.1906.00731"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20210903-213714292,
    title = "Zeroth-Order Methods for Convex-Concave Minmax Problems: Applications to Decision-Dependent Risk Minimization",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-213714292",
    id = "record",
    doi = "10.48550/arXiv.2106.09082"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20210903-213710817,
    title = "Fast Distributionally Robust Learning with Variance Reduced Min-Max Optimization",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-213710817",
    id = "record",
    doi = "10.48550/arXiv.2104.13326"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20210903-213646411,
    title = "Optimal Causal Imputation for Control",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-213646411",
    id = "record",
    doi = "10.48550/arXiv.1703.07049"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20210903-220351518,
    title = "On Thompson Sampling with Langevin Algorithms",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-220351518",
    id = "record",
    doi = "10.48550/arXiv.2002.10002"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20210903-213700306,
    title = "Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-213700306",
    id = "record",
    doi = "10.48550/arXiv.1907.03712"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20210903-213717702,
    title = "Who Leads and Who Follows in Strategic Classification?",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-213717702",
    id = "record",
    doi = "10.48550/arXiv.2106.12529"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215502,
    title = "2020 59th IEEE Conference on Decision and Control (CDC)",
    chapter = "Adaptive Control for Linearizable Systems Using On-Policy Reinforcement Learning",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215502",
    id = "record",
    isbn = "978-1-7281-7447-1",
    doi = "10.1109/CDC42340.2020.9304242"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215409,
    title = "2020 59th IEEE Conference on Decision and Control (CDC)",
    chapter = "High Confidence Sets for Trajectories of Stochastic Time-Varying Nonlinear Systems",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215409",
    id = "record",
    isbn = "978-1-7281-7447-1",
    doi = "10.1109/CDC42340.2020.9304491"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215578,
    title = "2020 59th IEEE Conference on Decision and Control (CDC)",
    chapter = "Expert Selection in High-Dimensional Markov Decision Processes",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215578",
    id = "record",
    isbn = "978-1-7281-7447-1",
    doi = "10.1109/CDC42340.2020.9303788"
}


@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"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215650,
    title = "2020 IEEE International Conference on Robotics and Automation (ICRA)",
    chapter = "Feedback Linearization for Uncertain Systems via Reinforcement Learning",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215650",
    id = "record",
    isbn = "978-1-7281-7395-5",
    doi = "10.1109/ICRA40945.2020.9197158"
}


@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"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215800,
    title = "2019 IEEE 58th Conference on Decision and Control (CDC)",
    chapter = "Local Nash Equilibria are Isolated, Strict Local Nash Equilibria in 'Almost All' Zero-Sum Continuous Games",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215800",
    id = "record",
    isbn = "978-1-7281-1398-2",
    doi = "10.1109/CDC40024.2019.9030203"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20210903-213653378,
    title = "On Finding Local Nash Equilibria (and Only Local Nash Equilibria) in Zero-Sum Games",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-213653378",
    id = "record",
    doi = "10.48550/arXiv.1901.00838"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215867,
    title = "2018 IEEE Conference on Decision and Control (CDC)",
    chapter = "On the Analysis of Cyclic Drug Schedules for Cancer Treatment using Switched Dynamical Systems",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215867",
    id = "record",
    isbn = "978-1-5386-1395-5",
    doi = "10.1109/CDC.2018.8619490"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215940,
    title = "2017 IEEE 56th Annual Conference on Decision and Control (CDC)",
    chapter = "Gradient-based inverse risk-sensitive reinforcement learning",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215940",
    id = "record",
    isbn = "978-1-5090-2873-3",
    doi = "10.1109/CDC.2017.8264535"
}


@other{https://resolver.caltech.edu/CaltechAUTHORS:20210903-213649911,
    title = "A Multi-Armed Bandit Approach for Online Expert Selection in Markov Decision Processes",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-213649911",
    id = "record",
    doi = "10.48550/arXiv.1707.05714"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215263,
    title = "2016 IEEE 55th Conference on Decision and Control (CDC)",
    chapter = "To observe or not to observe: Queuing game framework for urban parking",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215263",
    id = "record",
    isbn = "978-1-5090-1837-6",
    doi = "10.1109/CDC.2016.7799079"
}


@inbook{https://resolver.caltech.edu/CaltechAUTHORS:20210903-222216008,
    chapter = "Understanding the impact of parking on urban mobility via routing games on queue-flow networks",
    url = "https://resolver.caltech.edu/CaltechAUTHORS:20210903-222216008",
    id = "record",
    doi = "10.1109/CDC.2016.7799444"
}