Will Liang
@willjhliang
Unveiling DrEureka, an LLM-powered method for automatically designing reward and physics parameters for sim-to-real robot learning! We taught our robot dog to balance on a yoga ball and took it on a walk around campus. Check out our videos and website!
eureka-research.github.io/dr-eureka/
eureka-research.github.io/dr-eureka/
Jason Ma@JasonMa2020 · May 3, 2024Introducing DrEureka🎓, our latest effort pushing the frontier of robot learning using LLMs!
DrEureka uses LLMs to automatically design reward functions and tune physics parameters to enable sim-to-real robot learning. DrEureka can propose effective sim-to-real configurations
DrEureka uses LLMs to automatically design reward functions and tune physics parameters to enable sim-to-real robot learning. DrEureka can propose effective sim-to-real configurations
0:24 2 20