We are interested in the control of complex movements in animals and robots. Biological movements can be modeled in detail using optimality principles - which is not surprising given that they are shaped by iterative optimization processes such as evolution, learning, adaptation. Similarly, the best way to engineer a complex control system is to specify a high-level performance criterion and leave the details to numerical optimization. In both areas, the main difficulty lies in actually performing the optimization. Thus our focus is on developing more powerful methods for optimal control and applying them to harder problems. A key tool we use is the MuJoCo physics engine.
Vikash Kumar is now Research Scientist at OpenAI.
Galen Andrew is now Research Scientist at Google.
Igor Mordatch is now Research Scientist at OpenAI.
Joseph Xu is now Postdoctoral Fellow at Yale.
Tom Erez is now Research Scientist at DeepMind.
Yuval Tassa is now Research Scientist at DeepMind.
Krishnamurthy Dvijotham is now Research Scientist and PNNL.
Evangelos Theodorou is now Assistant Professor at Georgia Tech.