000			01694nam a22002177a 4500
008			220502b ||||| |||| 00| 0 eng d
020			_a9781886529106 (hb.)
082			_a519.703 _bBER
100			_aBertsekas, Dimitri P. _9809
245			_aNeuro-dynamic programming
260			_aMassachusetts _bAthena Scientific _c1996
300			_axiii, 491p.,
500			_ahttp://athenasc.com/ndpbook.html
520			_a"This is the first textbook that fully explains the neuro-dynamic programming/reinforcement learning methodology, which is a recent breakthrough in the practical application of neural networks and dynamic programming to complex problems of planning, optimal decision making, and intelligent control. Neuro-dynamic programming uses neural network approximations to overcome the ""curse of dimensionality"" and the ""curse of modeling"" that have been the bottlenecks to the practical application of dynamic programming and stochastic control to complex problems. The methodology allows systems to learn about their behavior through simulation, and to improve their performance through iterative reinforcement. This book provides the first systematic presentation of the science and the art behind this exciting and far-reaching methodology. The book develops a comprehensive analysis of neuro-dynamic programming algorithms, and guides the reader to their successful application through case studies from complex problem areas."
650			_aReinforcement learning _9859
650			_aMathematical optimization _9688
650			_aNeural networks (Computer science) _9567
650			_aDynamic programming _9640
700			_aTsitsiklis, John N. _9810
942			_cBK
999			_c7854 _d7854