Algorithms for reinforcement learning
Auteur :
Szepesvári, Csaba
Éditeur :
Springer International Publishing AG
ISBN :
9783031004230
Date de publication :
7 juil. 2010
Dimensions :
23,5 x 19,1 cm
Langue :
Anglais
Pays d'origine :
Suisse
Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner's predictions.