Joongkyu Lee is a Ph.D. candidate in the Graduate School of Data Science at Seoul National University, under the supervision of Prof. Min-hwan Oh. He received MS in the Graduate School of Data Science under the supervison of Prof. Min-hwan Oh from Seoul National University, and BS in Industrial Engineering from Yonsei University.

His primary research interests are in sequential decision making, reinforcement learning, bandit algorithms, statstical machine learning, optimization for machine learning and their practical applications. His ultimate research goal is to develop algorithms that are both theoretically provable and practically implementable.

Interests
  • Sequential Decision Making
  • Reinforcement Learning
  • Bandit Algorithms
  • Statistical Machine Learning
  • Optimization
Education
  • Ph.D. candidate in Data Science, 2023 - Present

    Seoul National University

  • MS in Data Science, 2023

    Seoul National University

  • BS in Industrial Engineering, 2016

    Yonsei University

Recent Publications & Preprints

(2024). Nearly Minimax Optimal Regret for Multinomial Logistic Bandit. NeurIPS 2024.

PDF

(2024). Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation. NeurIPS 2024.

PDF

(2024). Demystifying Linear MDPs and Novel Dynamics Aggregation Framework. ICLR 2024.

PDF