All Recordings

Foundation Reward Models for Robot Learning

About This Talk

Learn how reward models enable scalable robot learning across diverse manipulation tasks. Dyna Robotics' Jason Ma discusses reinforcement learning for robots, scaling robot training, and how foundation reward models improve generalization. Presented at Actuate, Foxglove's annual robotics developer conference.

Speaker

Jason Ma, Co-founder, Dyna Robotics

Jason Ma is co-founder at Dyna Robotics. He received his PhD from University of Pennsylvania, where he studied scalable reinforcement learning algorithms and foundation models for robot learning. His research has been recognized with honors such as RSS Pioneers, Apple and OpenAI Fellowship, Best Paper Finalist at ICRA 2024, Top 10 NVIDIA Research Projects of 2023, and covered by popular media such as the Economist, Fox, Yahoo, and TechCrunch.

More Recordings