- Paper “Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization” accepted to NeurIPS 2025
- Paper “Relaxed Transition Kernels can Cure Underestimation in Adversarial Offline Reinforcement Learning” accepted to ACML 2025
- Paper “Extending Automatic Machine Translation Evaluation to Book-Length Documents” accepted to EMNLP 2025
- Paper “Action-Constrained Imitation Learning” accepted to ICML 2025
- Papers “Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPs” and “BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL” accepted to ICLR 2025
- Paper “Offline Imitation of Badminton Player Behavior via Experiential Contexts and Brownian Motion” accepted to ECML-PKDD 2024
- Papers “Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning” and “Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement Learning” accepted to ICML 2024
- Lab members received multiple awards including the 18th Taiwan Management Institute Thesis Award and Hon Hai Technology Award
Research Experience
- Associate Professor at the Department of Computer Science, National Yang Ming Chiao Tung University
- Invited to serve as an Area Chair of ICLR 2026
Background
- Research Interests: Bandit Learning, Reinforcement Learning, Bayesian Optimization, Meta Learning, Optimization for Networks
- Professional Field: Computer Science
- Biography: Associate Professor at the Department of Computer Science, National Yang Ming Chiao Tung University, focusing on reinforcement learning and related areas