• An Evaluation of GUI and Kinesthetic Teaching Methods for Constrained-Keyframe Skills 

      Kurenkov, Andrey (Georgia Institute of Technology, 2015-08-18)
      Keyframe-based Learning from Demonstration has been shown to be an effective method for allowing end-users to teach robots skills. I propose a method for using multiple keyframe demonstrations to learn skills as sequences ...
    • Learning to Compose Skills 

      Tejani, Farhan
      We present a differentiable framework capable of learning a wide variety of compositions of simple policies that we call skills. By recursively composing skills with themselves, we can create hierarchies that display complex ...
    • State Space Decomposition in Reinforcement Learning 

      Kumar, Saurabh
      Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, ...