Talks & Presentations
Slides and posters from my talks and presentations are listed below.
Talks
- Bellman Optimality of Average-Reward Robust Markov Decision Processes with a Constant Gain
- Slides: INFORMS 2025
- Presented at INFORMS 2025 and INI workshop Bridging Stochastic Control and Reinforcement Learning 2025.
- Efficient Gradient Estimation for Overparameterized Stochastic Differential Equations
- Slides: APS Best Student Paper
- Presentation for the 2025 APS Best Student Paper competition at INFORMS 2025.
- Statistical Learning of Distributionally Robust Stochastic Control in Continuous State Spaces
- Slides: INFORMS 2024 and ICCOPT 2025
- Presented at INFORMS 2024 and ICCOPT 2025.
- On the Foundation of Distributionally Robust Reinforcement Learning (Long version)
- Slides: Stanford and Berkeley talks
- Presented at Stanford and Berkeley seminars 4/2024.
- On the Foundation of Distributionally Robust Reinforcement Learning
- Slides: CISS 2024
- Conference on Information Sciences and Systems (CISS) 2024.
- Reinforcement Learning for Mixing Systems
- Slides: INFORMS 2023
- Presented at INFORMS 2023.
- Distributionally Robust Q-learning: Formulations, Algorithms, and Sample Complexities
- Slides: SIAM OP23
- Presented at SIAMOP 2023.
- Distributionally Robust Q-learning: Algorithm Designs and Sample Complexities
- Presented at Stanford OR Seminar.
- A Finite Sample Complexity Bound for the Distributionally Robust Q-learning
- Presented at INFORMS 2022.
Posters
- Optimal Sample Complexity for Average Reward Markov Decision Processes
- Poster: AISTATS 23 DRQL
- Presented at ICLR 2024
- A Finite Sample Complexity Bound for the Distributionally Robust Q-learning
- Poster: AISTATS 23 DRQL
- Presented at AISTATS 2023