000			02950nam a22003735i 4500
001			293419
003			MX-SnUAN
005			20170705134227.0
007			cr nn 008mamaa
008			150903s2005 gw | o |||| 0|eng d
020			_a9783540268772 _99783540268772
024	7		_a10.1007/b138233 _2doi
035			_avtls000346753
039		9	_a201509030433 _bVLOAD _c201405070510 _dVLOAD _y201402070904 _zstaff
040			_aMX-SnUAN _bspa _cMX-SnUAN _erda
050		4	_aQ334-342
100	1		_aHutter, Marcus. _eautor _9325991
245	1	0	_aUniversal Artificial Intellegence : _bSequential Decisions Based on Algorithmic Probability / _cby Marcus Hutter.
264		1	_aBerlin, Heidelberg : _bSpringer Berlin Heidelberg, _c2005.
300			_axx, 278 páginas _brecurso en línea.
336			_atexto _btxt _2rdacontent
337			_acomputadora _bc _2rdamedia
338			_arecurso en línea _bcr _2rdacarrier
347			_aarchivo de texto _bPDF _2rda
490	0		_aTexts in Theoretical Computer Science An EATCS Series
500			_aSpringer eBooks
505	0		_aShort Tour Through the Book -- Simplicity & Uncertainty -- Universal Sequence Prediction -- Agents in Known Probabilistics Environments -- The Universal Algorithmic Agent AIXI -- Important Environmental Classes -- Computational Aspects -- Discussion.
520			_aDecision Theory = Probability + Utility Theory + + Universal Induction = Ockham + Bayes + Turing = = A Unified View of Artificial Intelligence This book presents sequential decision theory from a novel algorithmic information theory perspective. While the former is suited for active agents in known environments, the latter is suited for passive prediction in unknown environments. The book introduces these two well-known but very different ideas and removes the limitations by unifying them to one parameter-free theory of an optimal reinforcement learning agent embedded in an arbitrary unknown environment. Most if not all AI problems can easily be formulated within this theory, which reduces the conceptual problems to pure computational ones. Considered problem classes include sequence prediction, strategic games, function minimization, reinforcement and supervised learning. The discussion includes formal definitions of intelligence order relations, the horizon problem and relations to other approaches to AI. One intention of this book is to excite a broader AI audience about abstract algorithmic information theory concepts, and conversely to inform theorists about exciting applications to AI.
590			_aPara consulta fuera de la UANL se requiere clave de acceso remoto.
710	2		_aSpringerLink (Servicio en línea) _9299170
776	0	8	_iEdición impresa: _z9783540221395
856	4	0	_uhttp://remoto.dgb.uanl.mx/login?url=http://dx.doi.org/10.1007/b138233 _zConectar a Springer E-Books (Para consulta externa se requiere previa autentificación en Biblioteca Digital UANL)
942			_c14
999			_c293419 _d293419