Sang Hyoung Lee — accepted AI-conference papers

2021

Acceleration of Actor-Critic Deep Reinforcement Learning for Visual Grasping by State Representation Learning Based on a Preprocessed Input Image

Taewon Kim, Yeseong Park, Youngbin Park, Sang Hyoung Lee, Il Hong Suh

IROS 2021poster

For robotic grasping tasks with diverse target objects, some deep learning-based methods have achieved state-of-the-art results using direct visual input. In contrast, actor-critic deep reinforcement learning (RL) methods typically perform very poorly when applied to grasp diverse objects, especiall…

Cited by 8 Source ↗Scholar ↗

2021

Sim-to-Real Visual Grasping via State Representation Learning Based on Combining Pixel-Level and Feature-Level Domain Adaptation

Youngbin Park, Sang Hyoung Lee, Il Hong Suh

ICRA 2021poster

In this study, we present a method to grasp diverse unseen real-world objects using an off-policy actor-critic deep reinforcement learning (RL) with the help of a simulation and the use of as little real-world data as possible. Actor-critic deep RL is unstable and difficult to tune when a raw image…

Cited by 10 Source ↗Scholar ↗

2019

Relationship Between the Order for Motor Skill Transfer and Motion Complexity in Reinforcement Learning

Nam Jun Cho, Sang Hyoung Lee, Il Hong Suh, Hong-Seok Kim

RA-L 2019

We propose a method to generate an order for learning and transferring motor skills based on motion complexity, then evaluate the order to learn motor skills of a task and transfer them to another task as a form of reinforcement learning (RL). Here, motion complexity refers to the complexity calcula

Cited by 6 Source ↗Scholar ↗