Gawon Lee

PhD Candidate at SNU

I want to bridge the gap between high-level decision-making and complex physical control by developing sample-efficient, scalable learning frameworks. My academic mission is to pioneer autonomous robotic systems that can generalize across diverse, real-world tasks.

Research Areas

Reinforcement Learning

Goal-Conditioned RL, Multi-Task RL, RL Fine-Tuning VLA Models

Recent Publications

FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance

Submitted to Advances in Neural Information Processing Systems (NeurIPS) • 2026

Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement Learning

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) • 2025