Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery
Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new downstream tasks due to the innate task-specific training...
In spring 2018, I joined LARR (formerly known as ICSL) under the supervision of Prof. H. Jin Kim at Seoul National University.
My research interests are at the intersection of Reinforcement Learning, Machine Learning and Robotics. I am collaborating with J. Hyeon Park, Daesol Cho and Seungjae Lee.
Recent posts
Automating Reinforcement Learning with Example-based Resets
Deep reinforcement learning has enabled robots to learn motor skills from environmental interactions with minimal to no prior knowledge. However, existing re...
(submitted) Distributed multi-agent target search and tracking with Gaussian process and reinforcement learning
Deploying multiple robots for target search and tracking has many practical applications, yet the challenge of planning over unknown or partially known targe...