Reinforcementlearning,oneofthemostactiveresearchareasinartificialintelligence,isacomputationalapproachtolearningwherebyanagenttriestomaximizethetotalamountofrewarditreceiveswheninteractingwithacomplex,uncertainenvironment.InReinforcementLearning,RichardSuttonandAndrewBartoprovideaclear