I'm a Ph.D. student at the Hong Kong University of Science and Technology (2023–present). Previously, I received my bachelor's degree in Computer Science from Harbin Institute of Technology (2019–2023). I study how to build real-robot reinforcement learning systems that can be deployed quickly, generalize across tasks and environments, scale with data and interaction, and automate continual improvement on physical hardware.
Expected Ph.D. completion in 2027. I am seeking full-time research roles where I can contribute to scalable robot learning, VLA systems, and reliable deployment on real hardware.
ryangap@connect.ust.hk | Google Scholar | GitHub | Publications | News
Evaluation, post-training, and stable RL for continual improvement on hardware.
RL-generated skills and trajectories for scalable VLA pretraining.
Exploration-driven objectives for diverse, reusable behaviors.
