[Abstract]
"... the current paper, like the previous paper [Pch2003], studies the case when the environment is only partially observable."

     [Pch2003] Pchelkin A. Efficient exploration in reinforcement learning based on Utile Suffix Memory, journal Informatica, Lithuanian Academy of Sciences, Vol.14., 2003 => done


Efficient-exploration-in-reinforcement-learning-based-on-Utile-Suffix-Memory