 Neural Operator based Reinforcement Learning for Control of first-order PDEs with Spatially-Varying State DelayIFAC-PapersOnLine (IFAC-PapersOnLine), 2025 |
 Controlgym: Large-Scale Control Environments for Benchmarking
Reinforcement Learning AlgorithmsConference on Learning for Dynamics & Control (L4DC), 2023 |
 Provable Sim-to-real Transfer in Continuous Domain with Partial
ObservationsInternational Conference on Learning Representations (ICLR), 2022 |
 Learning-Based Adaptive Control for Stochastic Linear Systems with Input
ConstraintsIEEE Control Systems Letters (L-CSS), 2022 |
 Thompson Sampling Achieves Regret in Linear
Quadratic ControlAnnual Conference Computational Learning Theory (COLT), 2022 |
 |
 Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic
SystemsNeural Information Processing Systems (NeurIPS), 2022 |
 Online Algorithms and Policies Using Adaptive and Machine Learning
ApproachesIEEE Transactions on Automatic Control (IEEE TAC), 2021 |
