Scholar
Giseung Park
Google Scholar ID: M0n5A0AAAAAJ
Korea Advanced Institute of Science and Technology (KAIST)
Citations & Impact
Citations
66
H-index
3
i10-index
1
Publications
15
Co-authors
11
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publications:
- - Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach (NeurIPS 2025)
- - Sparse-reward RL paper accepted by Neurocomputing
- - Reward dimension reduction in MORL paper accepted by ICLR 2025
- - Involved in a Korea-Israel international research project, paper accepted by ICML 2024
Research Experience
- Currently a postdoctoral researcher at the University of Toronto, working with Prof. Florian Shkurti. Participated in the AI Hub Project funded by the Korean government, focusing on multi-modal RL-based decision-making.
Education
- Ph.D. from Korea Advanced Institute of Science and Technology (KAIST), supervised by Prof. Youngchul Sung.
Background
- Research interests include reinforcement learning (particularly partially observable RL and multi-objective RL), constrained RL, multi-agent systems, and multi-modal RL. Committed to developing efficient and user-friendly algorithms to tackle real-world problems.
Miscellany
- Contact: giseung.park@utoronto.ca, giseung.park1@gmail.com
