Soo Wung Shin

Soo Wung Shin

Auto-generated profile, based on publicly available information

Soo Wung Shin

Jinhakapply Corporation, Seoul, Republic of Korea

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 August 2022 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
SRSeung Min Ryu
Seung Min Ryu
KSKeewon Shin
Keewon Shin
SSSoo Wung Shin
Soo Wung Shin
SLSun Ho Lee
Sun Ho Lee
SSSu Min Seo
Su Min Seo
Namkug KimNamkug Kim
Namkug Kim


3 February 2026 in IEEE Access
Verified
Journal Article
Open access
MLMin Whoo Lee
Min Whoo Lee
YLYunsu Lee
Yunsu Lee
KKKibeom Kim
Kibeom Kim
SSSoo Wung Shin
Soo Wung Shin
JLJun Ki Lee
Jun Ki Lee
BZByoung-Tak Zhang
Byoung-Tak Zhang
Applying multi-agent reinforcement learning (MARL) to real-world scenarios is challenging because agents often need to adapt quickly to unexpected situations, including those rarely or never encountered in training. Recent methods for out-of-distribution generalization are unsuitable for applications on out-of-distribution tasks with limited communication, because they are typically restricted to centralized training or some specialized instances of distribution shifts. To address this limitation, we introduce the Unexpectedness Encoding Scheme, a new decentralized MARL algorithm in which agents communicate ‘‘unexpectedness,’’ the surprising aspects of the environment. In addition to sending their usual reward-driven messages, each agent predicts the next observation based on past experience and then compares this prediction with the actual outcome. The discrepancy between the two is encoded as a message, enabling agents to adapt more effectively to sudden or extreme changes. Experimental results on multi-agent cooperative tasks demonstrate that our method adapts robustly to both dynamically changing training environments and previously unseen out-of-distribution scenarios.