Will Liang
@willjhliang
Introducing Eureka, an open-ended agent for superhuman-level reward design! Awesome project led by @JasonMa2020. I’m so grateful to him and @AnimaAnandkumar @DrJimFan @yukez for their guidance and mentorship!
Jim Fan@DrJimFan · Oct 20, 2023Can GPT-4 teach a robot hand to do pen spinning tricks better than you do?
I'm excited to announce Eureka, an open-ended agent that designs reward functions for robot dexterity at super-human level. It’s like Voyager in the space of a physics simulator API!
Eureka bridges the
I'm excited to announce Eureka, an open-ended agent that designs reward functions for robot dexterity at super-human level. It’s like Voyager in the space of a physics simulator API!
Eureka bridges the
0:24 2 15