LEADER 03095oam 2200637I 450 001 9910785112203321 005 20220428164944.0 010 $a1-351-83382-0 010 $a1-315-21793-7 010 $a1-282-90296-2 010 $a9786612902963 010 $a1-4398-2109-7 024 7 $a10.1201/9781439821091 035 $a(CKB)2670000000047153 035 $a(EBL)589872 035 $a(OCoLC)666378166 035 $a(SSID)ssj0000426925 035 $a(PQKBManifestationID)11302179 035 $a(PQKBTitleCode)TC0000426925 035 $a(PQKBWorkID)10390207 035 $a(PQKB)10539407 035 $a(MiAaPQ)EBC589872 035 $a(Au-PeEL)EBL589872 035 $a(CaPaEBR)ebr10419897 035 $a(CaONFJC)MIL290296 035 $a(PPN)168822601 035 $a(EXLCZ)992670000000047153 100 $a20180331d2010 uy 0 101 0 $aeng 135 $aur|n|---||||| 181 $ctxt 182 $cc 183 $acr 200 00$aReinforcement learning and dynamic programming using function approximators /$f/ Lucian Busoniu. [et al] 210 1$aBoca Raton :$cCRC Press,$d2010. 215 $a1 online resource (285 p.) 225 1 $aAutomation and control engineering 300 $aDescription based upon print version of record. 311 $a1-4398-2108-9 320 $aIncludes bibliographical references and index. 327 $aCover; Title; Copyright; Preface; About the authors; Contents; 1 Introduction; 2 An introduction to dynamic programming and reinforcement learning; 3 Dynamic programming and reinforcement learning in large and continuous spaces; 4 Approximate value iteration with a fuzzy representation; 5 Approximate policy iteration for online learning and continuous-action control; 6 Approximate policy search with cross-entropy optimization of basis functions; Appendix A: Extremely randomized trees; Appendix B: The cross-entropy method; Symbols and abbreviations; Bibliography; List of algorithms; Index 330 $aFrom household appliances to applications in robotics, engineered systems involving complex dynamics can only be as effective as the algorithms that control them. While Dynamic Programming (DP) has provided researchers with a way to optimally solve decision and control problems involving complex dynamic systems, its practical value was limited by algorithms that lacked the capacity to scale up to realistic problems. However, in recent years, dramatic developments in Reinforcement Learning (RL), the model-free counterpart of DP, changed our understanding of what is possible. Those dev 410 0$aAutomation and control engineering. 606 $aDigital control systems 606 $aDynamic programming 615 0$aDigital control systems. 615 0$aDynamic programming. 676 $a629.8/9 701 $aBusoniu$b Lucian$01499569 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910785112203321 996 $aReinforcement learning and dynamic programming using function approximators$93725694 997 $aUNINA