Special Robotics Seminar: Understanding reinforcement learning on a deeper level

Dr Sang Wan Lee will discuss the latest research into advancing the understanding of human reinforcement learning.

Latest research in reinforcement learning (RL) has demonstrated an ability to succeed in a few arduous tasks. However, fundamental questions still remain as to how the human brain develops an ability to handle a wide variety of tasks and to learn from only few observations.

This talk introduces a research teams' twofold approach to advancing the understanding of human RL, by juxtaposing wisdoms from neuroscience and Artificial Intelligence (AI). The first line of research (AI to neuroscience) examines neural computations underlying RL. Dr Sang Wan Lee will summarize the recent neural findings about multiple distinctive types of RL to show how RL in humans and machines are different. The second line of research (neuroscience to AI) focuses on brain-inspired AI. He will also present two examples demonstrating the applicability of neuroscience for designing a better AI: RL algorithm to control human RL and designing an experiment without a human experimenter. A detailed insight into these issues not only permits advances in AI, but also helps us understand the nature of human intelligence on a deeper level.

About Dr Sang Wan Lee

Sang Wan Lee is currently an assistant professor within the department of bio and brain Engineering at KAIST, and the director of the laboratory for brain and machine intelligence. In 2009, he received a PhD in Electrical Engineering and Computer Science from KAIST. During 2010-2015, he was a postdoctoral associate at Mcgovern institute for brain research at MIT, followed by a Della Martin postdoctoral scholar in the Computation & Neural Systems and the Behavioral & Social Neuroscience program at Caltech. He was the recipient of the Della-Martin fellowship and the Google faculty research award for computational neuroscience. His research interests include brain-inspired artificial intelligence and computational neuroscience.

Further information

This seminar will be held in The Boardroom (8.01), EC Stoner Building