Daiki E. Matsunaga

PhD student, Korea Advanced Institute of Science & Technology

Joined

February 2022

Names

Daiki E. Matsunaga (Preferred)

Emails

****@ai.kaist.ac.kr (Confirmed)

,

****@gmail.com (Confirmed)

Personal Links

Career & Education History

PhD student

Korea Advanced Institute of Science & Technology (kaist.ac.kr)

2020 – Present

Advisors, Relations & Conflicts

PhD Advisor

2021 – Present

Expertise

Multi-Agent Reinforcement Learning

2020 – Present

Publications

Agent-Chained Policy Optimization
Daiki E. Matsunaga, Tri Wahyu Guntara, Junho Na, Scott Sanner, Pascal Poupart, Jongmin Lee, Kee-Eung Kim
- Submitted to ICLR 2026
- Readers: Everyone
CLEAR: An Information-Theoretic Framework for Distraction-Free Representation Learning in Visual Offline RL
Tri Wahyu Guntara, Daiki E. Matsunaga, HyeongJoo Hwang, Kee-Eung Kim
- Submitted to ICLR 2025
- Readers: Everyone
AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation
Daiki E. Matsunaga, Jongmin Lee, Jaeseok Yoon, Stefanos Leonardos, Pieter Abbeel, Kee-Eung Kim
- NeurIPS 2023 poster
- Readers: Everyone

Co-Authors