Ukjo Hwang

According to our database, Ukjo Hwang authored at least 7 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

QIPPO/CA: A Quantized Communication-Efficient MARL Framework for Fully Distributed Channel Access in Next-Generation Wireless Networks.

Sungweon Hong, Yeonseo Jeong, Ukjo Hwang, Songnam Hong

IEEE Internet Things J., 2026

2025

Federated Reinforcement Learning in Heterogeneous Environments.

Ukjo Hwang, Song-Nam Hong

CoRR, July, 2025

On Practical Robust Reinforcement Learning: Adjacent Uncertainty Set and Double-Agent Algorithm.

Ukjo Hwang, Songnam Hong

IEEE Trans. Neural Networks Learn. Syst., April, 2025

Moderate Actor-Critic Methods: Controlling Overestimation Bias via Expectile Loss.

Ukjo Hwang, Songnam Hong

CoRR, April, 2025

A Fully Independent MARL for Collision Avoidance in Distributed Channel Access.

Sungweon Hong, Yeonseo Jeong, Ukjo Hwang, Songnam Hong

Proceedings of the 102nd IEEE Vehicular Technology Conference, 2025

Tackling Environment Heterogeneity in Federated Reinforcement Learning.

Ukjo Hwang, Hyung-Taig Lim, Songnam Hong

Proceedings of the IEEE Conference on Artificial Intelligence, 2025

2023

On Practical Robust Reinforcement Learning: Practical Uncertainty Set and Double-Agent Algorithm.

Ukjo Hwang, Songnam Hong

CoRR, 2023