- A Dual Accelerated Method for Online Stochastic Distributed Averaging: From Consensus to Decentralized Policy Evaluation, with Ashwin Pananjady and Justin Romberg, under review by IEEE Transactions on Automatic Control.
Preliminary version was accepted by IEEE Conference on Decision and Control 2022.
- Finite Sample Analysis of Average-Reward TD Learning and Q-Learning, with Zhe Zhang and Siva Theja Maguluri, NeurIPS 2021 (acceptance rate 26%)[talk][code].
- DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning, with Daochen Zha, Jingru Xie, Wenye Ma, Xiangru Lian, Xia Hu and Ji Liu, ICML 2021 (acceptance rate 21.5%)[code][demo].
- Self-Diagnostic Mobile App: Common Bile Duct Stone Evaluation for Pediatric Patients, with Hongzhen Tian, Reuven Zev Cohen, Yajun Mei and A. Jay Freeman, The 2020 NASPGHAN Annual Conference.
- Finite-Sample Analysis of Nonlinear Stochastic Approximation with Applications in Reinforcement Learning, with Zaiwei Chen, Thinh T. Doan, Siva Theja Maguluri and John-Paul Clarke, Automatica [code].
- Performance of Q-learning with Linear Function Approximation: Stability and Finite Time Analysis, with Zaiwei Chen, Thinh T. Doan, Siva Theja Maguluri and John-Paul Clarke, NeurIPS 2019 Optimization Foundations for Reinforcement Learning Workshop.
- Inventory Replenishment Control under Supply and Demand Uncertainty, with Huan Xu and Chelsea White, Supported by Samsung Electronics Co., Ltd.
- Hierarchical Temporal Regularized Matrix Factorization for High-Dimensional Demand Forecasting with Missing Values, with Ming Li, Alibaba’s Internal Conference 2018.
- Automatic Event Detection in Basketball using HMM with Energy based Defensive Assignment, with Suraj Keshri, Min-hwan Oh and Garud Iyengar, The Journal of Quantitative Analysis in Sports 15(2), 141-153.