ThetopicofthisbookisReinforcementLearning—whichisasubfieldofMachineLearning—focusingonthegeneralandchallengingproblemoflearningoptimalbehaviorincomplexenvironment.Thelearningprocessisdrivenonlybyrewardvalueandobservationsobtainedfromtheenvironment.Thismodelisverygeneralandcanbeapplie