Teaching/Talks
Events in reversed chronological order.
Selected Talks
AAAI-25 Tutorial on Offline RL
- (2025/02) I will give a tutorial at AAAI-25 on "Advancing Offline Reinforcement Learning: Essential Theories and Techniques for Algorithm Developers".
The 2024 Young Researchers Workshop at Cornell ORIE
- (2024/10) Invited talk at Young Researchers Workshop on Sequential decision-making and Large Language Model Alignment. Thanks for the kind invitation!
The 25th International Symposium on Math Programming
- (2024/07) Invited talk at International Symposium on Math Programming about Deep RL target network learning in the function space!
2023 Informs Annual Meeting
- (2023/10) Invited for a community committee choice session talk at 2023 Informs Annual Meeting at Phoenix about Offline RL. Thanks Prof. Asu Ozdaglar and Prof. Kaiqing Zhang for the kind invitation!
AI Seminar at AI TIME
- (2023/06) Invited talk at AI TIME at Tsinghua University. Thanks for the kind invitation!
The 68th TrustML Young Scientist Seminar at RIKEN
- (2023/04) Invited talk at The TrustML Young Scientist Seminar at RIKEN. Thanks Director Masashi Sugiyama for the kind invitation!
Information Theory and Applications Workshop at San Diego
- (2023/02) Invited talk at the Information Theory and Applications Workshop at San Diego. Thanks ITA for the kind invitation!
Institute for Foundations of Data Science at Yale
- (2023/01) Invited talk at the Institute for Foundations of Data Science at Yale University about my work on offline Reinforcement Learning. Thanks Dan Spielman for the kind invitation!
Big Data and Machine Learning Seminar at UCLA
- (2022/04) Invited talk at Department of Computer Science, University of California, Los Angeles (UCLA) about my recent work on Instance-depedent offline Reinforcement Learning! See slides here!
Simons Institute workshop
- (2020/12) My paper Near-optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning is presented at Reinforcement Learning from Batch Data and Simulation workshop at Simons Institute. See details here!
RL theory seminars
- (2020/10) My paper Near-optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning is presented at RL theory seminars. See video here!
Coverage
MMMU
Our MMMU dataset is covered by Artificial Intelligence Index Report 2024, and reported in posts e.g. Gemini, Llama-3.2, and GPT-4o.
Mentoring
Early Research Scholar Program (ERSP)
I am mentoring an undergraduate team of 4 students of Early Research Scholar Program (ERSP) at UC, Santa Barbara for empirical benchmarking of offline policy learning methods for Reinforcement Learning. For an initial description of this program, see here.
Teaching Assistant
PSTAT213A: Probability Theory and Stochastic Processes
Graduate course, UC santa Barbara, Department of Statistics and Applied Probability
- Topics covered: Generating functions, discrete and continuous time Markov chains; random walks; branching processes; birth-death processes; Poisson processes, point processes. Time-reversibility, Coupling; Semigroup; Renewal Processes; Queuing Applications.
PSTAT160AB: Applied Stochastic Processes
Undergraduate course, UC santa Barbara, Department of Statistics and Applied Probability
- Topics covered: Conditional Expectation; Moment Generating Functions; Tail Bounds & Limit Theorems; Random Walk; Markov Chains; Simulation and Markov Chain Monte Carlo.
PSTAT120ABC: Probability and Statistics
Undergraduate course, UC santa Barbara, Department of Statistics and Applied Probability
- Topics covered: Jacobian method; Order statistics; Estimation Theory; Minimum Variance Unbiased Estimators; Method of Moments, Maximum Likelihood; Hypothesis Testing; Likelihood Ratio tests; Contingency tables; Bayesian estimators of binomial proportions; Bayesian credible sets.