Otterlo (computer science, Katholieke U. Leuven, Belgium) has synthesized the published literature on the practice since it began in 1998, keeping his eye always on the end product--a useful reference for researchers--rather than on maintaining a consistent and scientifically rigorous method of compression and summary. Moving from learning sequential decision-making under uncertainty to using it in the first-order setting, he covers concepts and algorithms of Markov decision processes (MDP); generalization and abstraction in them; reasoning, learning, and acting in worlds with objects; model-free and model-based algorithms for relational MDPs; and sapience, models, and hierarchy. Annotation ©2009 Book News, Inc., Portland, OR (booknews.com)
Le informazioni nella sezione "Riassunto" possono far riferimento a edizioni diverse di questo titolo.
EUR 6,44 per la spedizione da U.S.A. a Italia
Destinazione, tempi e costiDa: ThriftBooks-Atlanta, AUSTELL, GA, U.S.A.
Hardcover. Condizione: Fair. No Jacket. Readable copy. Pages may have considerable notes/highlighting. ~ ThriftBooks: Read More, Spend Less 1.01. Codice articolo G1586039695I5N00
Quantità: 1 disponibili
Da: dsmbooks, Liverpool, Regno Unito
Hardcover. Condizione: Acceptable. Acceptable. book. Codice articolo D8S0-3-M-1586039695-6
Quantità: 1 disponibili