Hyungho Na
Scholar

Hyungho Na

Google Scholar ID: KzZme2EAAAAJ
Postdoctoral Researcher, Korea Advanced Institute of Science and Technology
(Multi-agent) Reinforcement LearningRepresentation LearningMulti-agent systems
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
93
 
H-index
4
 
i10-index
3
 
Publications
20
 
Co-authors
2
list available
Contact
CVOpen ↗GitHubOpen ↗
Publications
2 items
Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment
2026
Cited
0
Trajectory-Class-Aware Multi-Agent Reinforcement Learning
2025
Cited
0
Resume (English only)
Academic Achievements
  • Selected Publications:
  • - [C] Trajectory-Class-Aware Multi-agent Reinforcement Learning
  • - [C] LAGMA: LAtent Goal-guided Multi-agent Reinforcement Learning
  • - [C] Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning
  • - [J] Weapon–target assignment by reinforcement learning with pointer network
  • - [J] Midcourse guidance strategy for multistage interceptors with coasting phase
  • - [J] Optimal arrangement of missile defense systems considering kill probability
  • Recent Awards and Scholarships:
  • - Global Leadership Awards (Challenge category), KAIST, 2025
  • - Character Scholarship (Merit category), KAIST, 2024
  • - Outstanding Champion (the 1st Place in the Challenge), Team AAILAB, ICML MFM-EAI Workshop, 2024
  • - Innovation Award, Team AAILAB, ICML MFM-EAI Workshop, 2024
  • - Achievement Award, Theater Defense Research Center, Agency for Defense Development, 2023
Research Experience
  • Worked at the Agency for Defense Development, participating in R&D for the missile defense system.
Education
  • PhD from KAIST in February 2025, advised by Prof. Il-chul Moon (AAILAB) and co-advised by Prof. Jaemyung Ahn (SAI).
Background
  • Research interests focus on building autonomous agents and enhancing their planning and execution capabilities across various domains. AI Core: (Multi-Agent) Reinforcement Learning, Representation Learning, Lifelong Learning, Multi-modal Foundation Model, Preference Optimization, and Embodied Agents. AI Applications: Sequential Decision-making, AI-transformed Defense Systems, and Operations for Complex Network Systems. G&C, Optimization and others: Guidance and Control (G&C), 6-DOF simulation, Military Operations, Filters, and Design Optimization of Aerospace Systems.
Miscellany
  • Contact: gudgh723 [at] gmail [dot] com / gudgh723 [at] kaist [dot] ac [dot] kr
  • [Google Scholar], [Github], [CV]
Co-authors
2 total
Co-author 1
Co-author 1
Il-Chul Moon
Il-Chul Moon
Professor, Department of Industrial and Systems Engineering, KAIST