Heechang Ryu

My Google Scholar, Linkedin

Please send me an email if you want my CV. (heechang.ryu21@gmail.com)

Staff Software Engineer / ML Researcher @ Samsung Research

KAIST Ph.D.

My current keywords are as follows:

Machine Learning

• Alignment learning for LLM • Preference optimization • Reinforcement learning from HF

• Instruction following for LLM • Prompting • Multi-agent reinforcement learning

Application

• Large language model (LLM) • Code generation model • Robot control

Programming

Main: • Python • C/C++ • PyTorch • TensorFlow

Possible: • Kotlin • C# • Lua • Matlab

Publications' highlights

REMAX: Relational Representation
for Multi-Agent Exploration

Ryu H., Shin H., and Park J., “REMAX: Relational Representation for Multi-Agent Exploration,” In Proceedings of the 21st International Conference on Autonomous Agents and MultiAgent Systems (AAMAS), pp. 1137-1145. 2022. (acceptance rate: 26%)

Paper

Cooperative and Competitive Biases
for Multi-Agent Reinforcement Learning

Ryu H., Shin H., and Park J., “Cooperative and Competitive Biases for Multi-Agent Reinforcement Learning,” In Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS), pp. 1091-1099. 2021. (acceptance rate: 24.8%)

Paper

Multi-Agent Actor-Critic
with Hierarchical Graph Attention Network

Ryu H., Shin H., and Park J., “Multi-Agent Actor-Critic with Hierarchical Graph Attention Network,” In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI), pp. 7236-7243. 2020. (acceptance rate: 20.6%)

Paper

Does Adam Optimizer Keep
Close to the Optimal Point?

Bae K.*, Ryu H.*, and Shin H. (* Co-first author), “Does Adam Optimizer Keep Close to the Optimal Point?,” NeurIPS2019 Workshop on Beyond First Order Methods in ML. 2019.

Paper

Multi-Agent Actor-Critic
with Generative Cooperative Policy Network

Ryu H., Shin H., and Park J., “Multi-Agent Actor-Critic with Generative Cooperative Policy Network,” arXiv preprint arXiv:1810.09206. 2018.

Paper

Energy Storage Control Based on User Clustering
and Battery Capacity Allocation

Ryu H., Jung Y., and Park J., “Energy Storage Control Based on User Clustering and Battery Capacity Allocation,” IEEE Power & Energy Society General Meeting, pp. 1-5. 2017.

Paper

Classification of Heart Sound Recordings
Using Convolution Neural Network

Ryu H., Park J., and Shin H., “Classification of Heart Sound Recordings Using Convolution Neural Network,” Computing in Cardiology Conference (CinC), pp. 1153-1156. 2016.

Paper