Task-Agnostic Online Reinforcement Learning with
     an Infinite Mixture of Gaussian Processes
    Mengdi Xu, Wenhao Ding, Jiacheng Zhu, Zuxin Liu, Baiming Chen, Ding Zhao
               Carnegie Mellon University
   {mengdixu, wenhaod, jzhu4, zuxinl, baimingc, dingzhao}@andrew.cmu.edu

                       Abstract
     Continuously learning to solve unseen tasks with limited experience has been
     extensively pursued in meta-learning and continual learning, but with restricted
     assump ...