Sang Wan Lee

About

Sang Wan Lee bridges the gap between biological and artificial intelligence, pioneering a truly interdisciplinary approach to decision-making. His research lies at the intersection of decision neuroscience, reinforcement learning, and human-robot interaction, with a core mission to build brain-inspired, autonomous systems that learn and adapt in real-world environments. Lee’s major contributions include developing a nonsupervised learning framework for discovering and predicting human behavior patterns from sequential actions—a crucial step for creating assistive robots that can intuitively understand and anticipate human needs. He has also championed the integration of insights from decision neuroscience into reinforcement learning, proposing novel architectures that are not only high-performance but also memory-efficient and fast, directly addressing the challenges of noise and unpredictability in dynamic settings. His work, including a highly cited 2019 paper advocating for interdisciplinary collaboration between neuroscience and robotics, has garnered over 50 citations. By systematically translating neural principles of decision-making into robotic algorithms, Lee is laying the groundwork for a new generation of intelligent, human-friendly service robots capable of seamless, adaptive interaction.

Research Focus

Key Achievements

Top Papers

1. 1
   A Nonsupervised Learning Framework of Human Behavior Patterns Based on Sequential Actions

   22 citations · 2009
2. 2
   Decision-making in brains and robots — the case for an interdisciplinary approach

   19 citations · 2019
3. 3
   Toward high-performance, memory-efficient, and fast reinforcement learning—Lessons from decision neuroscience

   12 citations · 2019
4. 4
   LEARNING TECHNIQUES IN SERVICE ROBOTIC ENVIRONMENT

   2 citations · 2006

Key Collaborators

Contact & Links