소장자료
LDR | 03159cam a2200529Ii 4500 | ||
001 | 0100557485▲ | ||
003 | OCoLC▲ | ||
005 | 20220524130822▲ | ||
006 | m d | ▲ | ||
007 | cr |||||||||||▲ | ||
008 | 190402s2018 maua ob 001 0 eng ▲ | ||
019 | ▼a1175918416▲ | ||
020 | ▼a9780262352703▼q(electronic bk.)▲ | ||
020 | ▼a0262352702▼q(electronic bk.)▲ | ||
020 | ▼z9780262039246▼q(hardcover▼qalkaline paper)▲ | ||
020 | ▼z0262039249▼q(hardcover▼qalkaline paper)▲ | ||
035 | ▼a2517937▼b(N$T)▲ | ||
035 | ▼a(OCoLC)1091191532▼z(OCoLC)1175918416▲ | ||
040 | ▼aINA▼beng▼erda▼epn▼cINA▼dYDX▼dUKAHL▼dOCLCQ▼dN$T▼dEBLCP▲ | ||
050 | 4 | ▼aQ325.6▼b.R45 2018▲ | |
082 | 0 | 4 | ▼a006.3/1▼223▲ |
100 | 1 | ▼aSutton, Richard S.▲ | |
245 | 1 | 0 | ▼aReinforcement learning▼h[electronic resource] :▼ban introduction /▼cRichard S. Sutton and Andrew G. Barto.▲ |
250 | ▼a2nd ed.▲ | ||
260 | ▼aCambridge, Massachusetts :▼bThe MIT Press,▼c[2018]▲ | ||
300 | ▼a1 online resource (xxii, 526 p.)▲ | ||
336 | ▼atext▼btxt▼2rdacontent▲ | ||
337 | ▼acomputer▼bc▼2rdamedia▲ | ||
338 | ▼aonline resource▼bcr▼2rdacarrier▲ | ||
490 | 1 | ▼aAdaptive computation and machine learning▲ | |
504 | ▼aIncludes bibliographical references and index.▲ | ||
505 | 0 | 0 | ▼g1.▼tIntroduction --▼gI.▼tTabular Solution Methods:▼g2.▼tMulti-armed Bandits --▼g3.▼tFinite Markov Decision processes --▼g4.▼tDynamic programming --▼g5.▼tMonte Carlo methods --▼g6.▼tTemporal-difference learning --▼g7.▼tn-step Bootstrapping --▼g8.▼tPlanning and learning with tabular methods--▼gI.▼tApproximate Solution Methods:▼g9.▼tOn-policy Prediction with Approximation--▼g10.▼tOn-policy Control with Approximation--▼g11.▼tO↵-policy Methods with Approximation --▼g12.▼tEligibility Traces--▼g13.▼tPolicy Gradient Methods--▼gIII.▼tLooking Deeper:▼g14.▼tPsychology --▼g15.▼tNeuroscience --▼g16.▼tApplications and Case Studies --▼g17.▼tFrontiers▲ |
520 | ▼a"Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the field's key ideas and algorithms."--▼cProvided by publisher.▲ | ||
590 | ▼aOCLC control number change▲ | ||
650 | 0 | ▼aReinforcement learning.▲ | |
650 | 7 | ▼aReinforcement learning.▼2fast▼0(OCoLC)fst01732553▲ | |
655 | 4 | ▼aElectronic books.▲ | |
700 | 1 | ▼aBarto, Andrew G.▲ | |
776 | 0 | 8 | ▼iPrint version:▼aSutton, Richard S.▼tReinforcement learning.▼bSecond edition.▼dCambridge, Massachusetts : The MIT Press, [2018]▼z0262039249▼z9780262039246▼w(DLC) 2018023826▼w(OCoLC)1043175824▲ |
830 | 0 | ▼aAdaptive computation and machine learning.▲ | |
856 | 4 | 0 | ▼3EBSCOhost▼uhttp://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&db=nlabk&AN=2517937▲ |
![](https://lib.pusan.ac.kr/wp-content/themes/pnul2022/assets/images/default/default_w_279X393.png)
Reinforcement learning : an introduction
자료유형
국외eBook
서명/책임사항
Reinforcement learning [electronic resource] : an introduction / Richard S. Sutton and Andrew G. Barto.
판사항
2nd ed.
발행사항
Cambridge, Massachusetts : The MIT Press , [2018]
형태사항
1 online resource (xxii, 526 p.)
서지주기
Includes bibliographical references and index.
내용주기
1. Introduction -- I. Tabular Solution Methods : 2. Multi-armed Bandits -- 3. Finite Markov Decision processes -- 4. Dynamic programming -- 5. Monte Carlo methods -- 6. Temporal-difference learning -- 7. n-step Bootstrapping -- 8. Planning and learning with tabular methods-- I. Approximate Solution Methods : 9. On-policy Prediction with Approximation-- 10. On-policy Control with Approximation-- 11. O↵-policy Methods with Approximation -- 12. Eligibility Traces-- 13. Policy Gradient Methods-- III. Looking Deeper : 14. Psychology -- 15. Neuroscience -- 16. Applications and Case Studies -- 17. Frontiers
요약주기
"Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the field's key ideas and algorithms."-- Provided by publisher.
기타형태저록
ISBN
9780262352703 0262352702
관련 인기대출 도서