Reinforcement Learning for Cost-Aware Markov Decision Processes

         Wesley A. Suttle 1 Kaiqing Zhang 2 Zhuoran Yang 3 David N. Kraemer 1 Ji Liu 4

              Abstract                quently used in practice. Nevertheless, alternative objectives
                                  have seen increasing interest, as researchers seek to extend
   Ratio maximization has applications in areas as        RL techniques to larger classes of problems and incorporate
   diverse as finance, reward sha ...