Research Areas
Research Areas
Currently, we are focusing on Reinforcement Learning (RL), which will be a major tool for AI robots, autonomous vehicles, smart cities, and large language models (LLMs) from various research perspectives such as
Improved value estimation
Enhancing exploration
Domain adaptation
Imitation learning
Partially-observable Markov decision processes (POMDPs)
Offline reinforcement learning
Multi-task and meta reinforcement learning
Multi-objective reinforcement learning
Multi-agent reinforcement learning
Multi-modal reinforcement learning
RL for large language models (LLMs)
LLM Agents: Core reasoning for AI robots
Applications to communication and control
SISReL belongs to the General Robotics Foundation Model research team of the National AI Hub Project, and we are investigating the theoretical aspects of robotics foundation models such as task-oriented LLM agent reasoning and low-level RL enabling diverse robot movements.
Foundation Model for General Robotics, National AI Hub Project (AI 연구 거점 프로젝트 ) (PI: Kee-Eung Kim, IITP, 2024.07 -)
Generative Model-based Efficient Reinforcement Learning Algorithms for Multi-modal Expansion in Generalized Environments (NRF, 2025.03 - )
Development of Artificial Intelligence Technology for Self-Improving Competency-Aware Learning Capabilities (IITP, 2022.04 - )
Development of Core Technologies for Task-Oriented Reinforcement Learning for Commercialization of Autonomous Drones (IITP, 2022.04 - )
Center for Applied Research in Artificial Intelligence (ADD, 2019.12 - )
Deep Multi-agent Reinforcement Learning of Markov Games for Distributed Traffic Management in Smart Cities (NRF Korea-Israel Joint Project, 2022.09 - 2024.08 )
Information Theory-Based Reinforcement Learning for Generalized Environments (NRF, 2021.03 - 2025.02)
Development of Disaster Response Algorithm through Internet Big Data Analysis Based on Artificial Intelligence (NRF, 2019.09 - 2022.09 )
Machine Learning-Based Edge Computing Operation Optimization (IITP, 2019.04 - 2021.12)
Information Geometry-Based Performance Enhancement for Policy-Based Reinforcement Learning with Large Action Spaces (NRF, 2017.09- 2021.08)
Research and Development of Adaptive Machine Learning Algorithms for Autonomous Digital Companion (IITP, 2016.12-2020.12)
Pattern Analysis and Anomoly Detection of AMI Smart Meter Data Based on Machine Learning Algorithms (KEPCO, 2016.05-2016.11)
5G Open Reference Model : Link Level Simulation (IITP, 2016.08- 2019.02)
5G Giga Korea Project (ETRI, 2014.07 - 2018.04)
Development of Fundamental Technologies for User-Centric 5G Mobile Personal Cells (ETRI, 2013.04-2016.02)
Can Modern Communication/Network Theories Inspire Brain Reverse Engineering and Vice Versa? (KAIST, 2011.06-2012.12)
Development of Adaptive Beam Multiple Access Technology without Interference Based on Antenna Node Grouping (KCC, 2011.03-2016.02)
Research on Interference Problem for Future Wireless Networks for Smartphone Era (NRF, 2010.09-2016.10)
Distributed Inference in Wireless Sensor Networks: Inference Machines on Network Graphs (KRF, 2009.01-2009.12, Global Research Nework Project. Collaboration with Princeton University)
5G Mobile Communication Systems Based on Beam Division Multiple Access and Relays with Group Cooperation (KCC, 2008.03-2013.02)
Next Generation Tactical Information Communication Network (ETRI, 2008.03-2010.02)
KAIST B4G System Core Technologies and Simulator Development (Samsung Electronics, 2007.05-2011.07)
An Integrative Design Approach to Wireless and Sensor Networks (KAIST, 2007.02-2009.12)