Now showing items 1-2 of 2

    • Hierarchical Planning and Control for Complex Motor Tasks 

      Zimmermann, Daniel; Coros, Stelian; Ye, Yuting; Sumner, Robert W.; Gross, Markus (ACM Siggraph, 2015)
      We present a planning and control framework that enables physically simulated characters to perform various types of motor tasks. To create physically-valid motion plans, our method uses a hierarchical set of simplified ...
    • Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter? 

      Peng, Xue Bin; Panne, Michiel van de (ACM, 2017)
      The use of deep reinforcement learning allows for high-dimensional state descriptors, but little is known about how the choice of action representation impacts learning and the resulting performance. We compare the impact ...