Páginas:106Géneros:12:UG:Graphical&digitalmediaapplications12:UYQ:ArtificialintelligenceSinopsis:Reinforcementlearningisalearningparadigmconcernedwithlearningtocontrolasystemsoastomaximizeanumericalperformancemeasurethatexpressesalong-termobjective.Whatdistinguishesreinforcementlearningfromsupervisedlearningisthatonlypartialfeedbackisgiventothelearneraboutthelearnerspredictions.Further,thepredictionsmayhavelongtermeffectsthroughinfluencingthefuturestateofthecontrolledsystem.Thus,timeplaysaspecialrole.Thegoalinreinforcementlearningistodevelopefficientlearningalgorithms,aswellastounderstandthealgorithmsmeritsandlimitations.Reinforcementlearningisofgreatinterestbecauseofthelargenumberofpracticalapplicationsthatitcanbeusedtoaddress,rangingfromproblemsinartificialintelligencetooperationsresearchorcontrolengineering.Inthisbook,wefocusonthosealgorithmsofreinforcementlearningthatbuildonthepowerfultheoryofdynamicprogramming.Wegiveafairlycomprehensivecatalogoflearningproblems,describethecoreideas,notealargenumberofstateoftheartalgorithms,followedbythediscussionoftheirtheoreticalpropertiesandlimitations._,
"Sinopsis" puede pertenecer a otra edición de este libro.
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. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms' merits and limitations. Reinforcement learning is of great interest because of the large number of practical applications that it can be used to address, ranging from problems in artificial intelligence to operations research or control engineering. In this book, we focus on those algorithms of reinforcement learning that build on the powerful theory of dynamic programming.We give a fairly comprehensive catalog of learning problems, describe the core ideas, note a large number of state of the art algorithms, followed by the discussion of their theoretical properties and limitations.
"Sobre este título" puede pertenecer a otra edición de este libro.
EUR 5,09 gastos de envío desde Reino Unido a Estados Unidos de America
Destinos, gastos y plazos de envíoLibrería: WeBuyBooks, Rossendale, LANCS, Reino Unido
Condición: Like New. Most items will be dispatched the same or the next working day. An apparently unread copy in perfect condition. Dust cover is intact with no nicks or tears. Spine has no signs of creasing. Pages are clean and not marred by notes or folds of any kind. Nº de ref. del artículo: wbs6652138501
Cantidad disponible: 1 disponibles
Librería: medimops, Berlin, Alemania
Condición: good. Befriedigend/Good: Durchschnittlich erhaltenes Buch bzw. Schutzumschlag mit Gebrauchsspuren, aber vollständigen Seiten. / Describes the average WORN book or dust jacket that has all the pages present. Nº de ref. del artículo: M01608454924-G
Cantidad disponible: 1 disponibles
Librería: SecondSale, Montgomery, IL, Estados Unidos de America
Condición: Very Good. Item in very good condition! Textbooks may not include supplemental items i.e. CDs, access codes etc. Nº de ref. del artículo: 00087521207
Cantidad disponible: 1 disponibles