profile photo
Seungeun (Ross) Rho

Hello! I’m a fourth-year Computer Science Ph.D. student at Georgia Tech, advised by Prof. Sehoon Ha. I received my Master's and Bachelor's degrees in Computer Science from Seoul National University. I also closely work with Prof. Xue Bin Peng and Prof. Danfei Xu.

My research focuses on reinforcement learning for embodied agents, particularly how they can autonomously discover diverse and meaningful skills. I am especially interested in leveraging different forms of guidance to facilitate skill discovery, ranging from language and reference motions to competitive self-play.

 

 

 

PhD in Computer Science
2023 -

Robotics AI Institute, Research Intern
2025 Jan - May

 

 

Publications
[New] Game-Guided Skill Discovery through Self-Play for Playable Agent Control

Seungeun Rho, Jeonghwan Kim, Xue Bin Peng, Sehoon Ha
Preprint

[Arxiv] [Playable Demo]

[New] PrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors

Seungeun Rho*, Wontaek Kim*, Danfei Xu, Sehoon Ha
Preprint

[Arxiv]

LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts

Seungeun Rho, Shamel Fahmi, Jeonghwan Kim, Arianna Ilvonen, Sehoon Ha, Gabriel Nelson
IEEE RA-L 2026

[Arxiv] [Project]

Reference Grounded Skill Discovery

Seungeun Rho, Aaron Trinh, Danfei Xu, Sehoon Ha
ICLR 2026

[Arxiv] [Project]

Flip Stunts on Bike-Like Robots using Iterative Motion Imitation

Jeonghwan Kim, Shamel Fahmi, Seungeun Rho, Sehoon Ha, Gabriel Nelson
ICRA 2026

[Arxiv] [Project] [Blog]

Switch4EAI: Leveraging Console Game Platform for Benchmarking Robotic Athletics

Tianyu Li, Jeonghwan Kim, Wontaek Kim, Donghoon Baek, Seungeun Rho, Sehoon Ha
CoRL Open-Source Hardware Workshop 2025

[Arxiv] [Project]

Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion

Seungeun Rho*, Kartik Garg*, Morgan Byrd, Sehoon Ha
CoRL 2025

[Arxiv] [Project]

Language Guided Skill Discovery

Seungeun Rho, Laura Smith, Tianyu Li, Sergey Levine, Xue Bin Peng, Sehoon Ha
ICLR 2025

[Arxiv] [Project]

Wing strain based flight control of flapping-wing drones through reinforcement learning

Taewi Kim*, Insic Hong*, Sunghoon Im*, Seungeun Rho*, [+19 more]
Nature Machine Intelligence 2024

[Paper]

Efficient Latent Variable Modeling for Knowledge-Grounded Dialogue Generation

Gunsoo Han, Daejin Jo, Daniel Wontae Nam, Eunseop Yoon, Taehwan Kwon, Seungeun Rho, Kyoung-Woon On, Chang D. Yoo, Sungwoong Kim
EMNLP Findings 2023

[Paper]

LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward

Daejin Jo, Sungwoong Kim, Daniel Wontae Nam, Taehwan Kwon, Seungeun Rho, Jongmin Kim, Donghoon Lee
NeurIPS 2022

[Arxiv] [pdf]

Creating Pro-Level AI for a Real-Time Fighting Game using Deep Reinforcement Learning

Inseok Oh*, Seungeun Rho*, Sangbin Moon, Seongho Son, Hyoil Lee, Jinyun Chung
AAAI 2021, RL in Games Workshop
IEEE Transactions on Games 2025, Outstanding Paper Award

[Arxiv]

* indicates equal contribution

 

 

Projects
[RL Competition] NeurIPS 22' IGLU Challenge - 1st place winner

2022

Our team, "happy_igpu," won both 1st place and the research prize.

[leaderboard]
[RL Competition] Google Research Football with Manchester City F.C. - Gold Medal

2021

As a team leader (of the team "liveinparis"), our agent, trained with fictitious self-play, ranked 6th out of 1,138 teams.

[leaderboard] [github] [approach]
MinimalRL - ★ +3.1K

2021

I implemented basic RL algorithms with minimal lines of codes including: PPO, SAC, ACER, A2C, A3C, DQN, DDPG, etc.

[github]
 

 


Scholarly Activities
  • CoRL 2026, ICRA 2026, TMLR 2026, RA-L 2026 - Reviewer
  • NeurIPS 2025, ICLR 2025 - Reviewer
  • NeurIPS 2024 - Reviewer
Mentoring

I have been fortunate to work with these wonderful students:

Teaching Experience
  • SPRING 2026, FALL 2025 - Reinforcement Learning Teaching Assistant (CS7642)
  • SPRING 2024 - Computer Animation Teaching Assistant (CS4496)