000 03506nam a22005535i 4500
001 978-0-387-69082-7
003 DE-He213
005 20161121230609.0
007 cr nn 008mamaa
008 100301s2007 xxu| s |||| 0|eng d
020 _a9780387690827
_9978-0-387-69082-7
024 7 _a10.1007/978-0-387-69082-7
_2doi
050 4 _aQA76.9.M35
072 7 _aPBD
_2bicssc
072 7 _aUYAM
_2bicssc
072 7 _aCOM018000
_2bisacsh
072 7 _aMAT008000
_2bisacsh
082 0 4 _a004.0151
_223
100 1 _aCao, Xi-Ren.
_eauthor.
245 1 0 _aStochastic Learning and Optimization
_h[electronic resource] :
_bA Sensitivity-Based Approach /
_cby Xi-Ren Cao.
264 1 _aBoston, MA :
_bSpringer US,
_c2007.
300 _aXX, 566 p. 119 illus. With 212 Problems.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
505 0 _aFour Disciplines in Learning and Optimization -- Perturbation Analysis -- Learning and Optimization with Perturbation Analysis -- Markov Decision Processes -- Sample-Path-Based Policy Iteration -- Reinforcement Learning -- Adaptive Control Problems as MDPs -- The Event-Based Optimization - A New Approach -- Event-Based Optimization of Markov Systems -- Constructing Sensitivity Formulas.
520 _aStochastic learning and optimization is a multidisciplinary subject that has wide applications in modern engineering, social, and financial problems, including those in Internet and wireless communications, manufacturing, robotics, logistics, biomedical systems, and investment science. This book is unique in the following aspects. (Four areas in one book) This book covers various disciplines in learning and optimization, including perturbation analysis (PA) of discrete-event dynamic systems, Markov decision processes (MDP)s), reinforcement learning (RL), and adaptive control, within a unified framework. (A simple approach to MDPs) This book introduces MDP theory through a simple approach based on performance difference formulas. This approach leads to results for the n-bias optimality with long-run average-cost criteria and Blackwell's optimality without discounting. (Event-based optimization) This book introduces the recently developed event-based optimization approach, which opens up a research direction in overcoming or alleviating the difficulties due to the curse of dimensionality issue by utilizing the system's special features. (Sample-path construction) This book emphasizes physical interpretations based on the sample-path construction.
650 0 _aComputer science.
650 0 _aComputer science
_xMathematics.
650 0 _aArtificial intelligence.
650 0 _aCalculus of variations.
650 0 _aProbabilities.
650 0 _aEngineering design.
650 0 _aControl engineering.
650 1 4 _aComputer Science.
650 2 4 _aDiscrete Mathematics in Computer Science.
650 2 4 _aEngineering Design.
650 2 4 _aControl.
650 2 4 _aArtificial Intelligence (incl. Robotics).
650 2 4 _aCalculus of Variations and Optimal Control; Optimization.
650 2 4 _aProbability Theory and Stochastic Processes.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer eBooks
776 0 8 _iPrinted edition:
_z9780387367873
856 4 0 _uhttp://dx.doi.org/10.1007/978-0-387-69082-7
912 _aZDB-2-SCS
950 _aComputer Science (Springer-11645)
999 _c501139
_d501139