000			03179nam a22004455i 4500
001			u375352
003			SIRSI
005			20160812084319.0
007			cr nn 008mamaa
008			101212s2010 gw | s |||| 0|eng d
020			_a9783642165900 _9978-3-642-16590-0
040			_cMX-MeUAM
050		4	_aQ334-342
050		4	_aTJ210.2-211.495
082	0	4	_a006.3 _223
100	1		_aFrommberger, Lutz. _eauthor.
245	1	0	_aQualitative Spatial Abstraction in Reinforcement Learning _h[recurso electrónico] / _cby Lutz Frommberger.
264		1	_aBerlin, Heidelberg : _bSpringer Berlin Heidelberg, _c2010.
300			_aXVII, 174 p. _bonline resource.
336			_atext _btxt _2rdacontent
337			_acomputer _bc _2rdamedia
338			_aonline resource _bcr _2rdacarrier
347			_atext file _bPDF _2rda
490	1		_aCognitive Technologies, _x1611-2482
505	0		_aFoundations of Reinforcement Learning -- Abstraction and Knowledge Transfer in Reinforcement Learning -- Qualitative State Space Abstraction -- Generalization and Transfer Learning with Qualitative Spatial Abstraction -- RLPR – An Aspectualizable State Space Representation -- Empirical Evaluation -- Summary and Outlook.
520			_aReinforcement learning has developed as a successful learning approach for domains that are not fully understood and that are too complex to be described in closed form. However, reinforcement learning does not scale well to large and continuous problems. Furthermore, acquired knowledge specific to the learned task, and transfer of knowledge to new tasks is crucial.   In this book the author investigates whether deficiencies of reinforcement learning can be overcome by suitable abstraction methods. He discusses various forms of spatial abstraction, in particular qualitative abstraction, a form of representing knowledge that has been thoroughly investigated and successfully applied in spatial cognition research. With his approach, he exploits spatial structures and structural similarity to support the learning process by abstracting from less important features and stressing the essential ones. The author demonstrates his learning approach and the transferability of knowledge by having his system learn in a virtual robot simulation system and consequently transfer the acquired knowledge to a physical robot. The approach is influenced by findings from cognitive science.   The book is suitable for researchers working in artificial intelligence, in particular knowledge representation, learning, spatial cognition, and robotics.
650		0	_aComputer science.
650		0	_aArtificial intelligence.
650	1	4	_aComputer Science.
650	2	4	_aArtificial Intelligence (incl. Robotics).
650	2	4	_aControl, Robotics, Mechatronics.
710	2		_aSpringerLink (Online service)
773	0		_tSpringer eBooks
776	0	8	_iPrinted edition: _z9783642165894
830		0	_aCognitive Technologies, _x1611-2482
856	4	0	_zLibro electrónico _uhttp://148.231.10.114:2048/login?url=http://link.springer.com/book/10.1007/978-3-642-16590-0
596			_a19
942			_cLIBRO_ELEC
999			_c203232 _d203232