Publications

Conferences

Lim, H. D., , Lee, D. (2025). A finite-time analysis of distributed Q-learning. To appear in RLC2025

Lim, H. D. , Lee, D. (2025). A primal-dual perspective for distributed TD-learning. To appear in IJCAI2025

Lim, H. D., & Lee, D. (2024). Regularized Q-learning. Advances in Neural Information Processing Systems, 37, 129855-129887.

Lee, D., & Lim, H. D. (2024). Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes. In 18th IEEE International Conference on Control and Automation, ICCA 2024 (pp. 960-967). IEEE Computer Society.

Lim, H. D., & Lee, D. (2023). Backstepping Temporal Difference Learning. In The Eleventh International Conference on Learning Representations.

Journals

Lim, H. D., & Lee, D. (2024). Finite-time analysis of asynchronous Q-learning under diminishing step-size from control-theoretic view. IEEE Access.

Lim, H. D., & Lee, D. (2024). Finite-Time Analysis of Temporal Difference Learning with Experience Replay. Transactions on Machine Learning Research.

Lee, D., Lim, H. D., Park, J., & Choi, O. (2022). New Versions of Gradient Temporal-Difference Learning. IEEE Transactions on Automatic Control, 68(8), 5006-5013.