The Value Equivalence Principle
      for Model-Based Reinforcement Learning

    Christopher Grimm          André Barreto, Satinder Singh, David Silver
  Computer Science & Engineering              DeepMind
    University of Michigan      {andrebarreto,baveja,davidsilver}@google.com
    crgrimm@umich.edu

                       Abstract
     Learning models of the environment from data is often viewed as an essential com-
     ponent to building intelligent reinforcement learning (RL) agents. T ...