메뉴 건너뛰기




Volumn , Issue , 2001, Pages 683-689

Solving factored MDPs via non-homogeneous partitioning

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM FOR SOLVING; BISIMULATIONS; HOMOGENEOUS PARTITION; NON-HOMOGENEOUS; NUMBER OF BLOCKS; SUCCESSIVE REFINEMENT; VALUE FUNCTIONS;

EID: 27344435920     PISSN: 10450823     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (7)

References (20)
  • 1
    • 0024680419 scopus 로고
    • Adaptive aggregation for infinite horizon dynamic programming
    • Dimitri P. Bertsekas and David A. Castañon. Adaptive aggregation for infinite horizon dynamic programming. IEEE Transactions on Automatic Control, 34(6):589-598, 1989.
    • (1989) IEEE Transactions on Automatic Control , vol.34 , Issue.6 , pp. 589-598
    • Bertsekas, D.P.1    Castañon, D.A.2
  • 3
    • 0012352653 scopus 로고    scopus 로고
    • Approximating value trees in structured dynamic programming
    • Craig Boutilier and Richard Dearden. Approximating value trees in structured dynamic programming. In Proceedings ICML-96, 1996.
    • Proceedings ICML-96, 1996
    • Boutilier, C.1    Dearden, R.2
  • 7
    • 84990553353 scopus 로고
    • A Model for Reasoning about Persistence and Causation
    • Thomas Dean and Keiji Kanazawa. A Model for Reasoning about Persistence and Causation. Computational Intelligence, pages 143-150, 1989.
    • (1989) Computational Intelligence , pp. 143-150
    • Dean, T.1    Kanazawa, K.2
  • 9
    • 0034272032 scopus 로고    scopus 로고
    • Bounded-parameter Markov decision processes
    • Robert Givan, Sonia Leach, and Thomas Dean. Bounded-parameter Markov decision processes. Artificial Intelligence, 122:71-109, 2000.
    • (2000) Artificial Intelligence , vol.122 , pp. 71-109
    • Givan, R.1    Leach, S.2    Dean, T.3
  • 11
    • 0038595393 scopus 로고
    • Technical Report CMU-CS-103, School of Computer Science, Carnegie Mellon University
    • Geoffrey J. Gordon. Stable function approximation in dynamic programming. Technical Report CMU-CS-103, School of Computer Science, Carnegie Mellon University, 1995.
    • (1995) Stable Function Approximation in Dynamic Programming
    • Gordon, G.J.1
  • 14
    • 84880688552 scopus 로고    scopus 로고
    • Computing factored value functions for policies in structured MDPs
    • Daphne Koller and Ronald Parr. Computing factored value functions for policies in structured MDPs. In Proceedings IJCAI-99, 1999.
    • Proceedings IJCAI-99, 1999
    • Koller, D.1    Parr, R.2
  • 15
    • 84880680664 scopus 로고    scopus 로고
    • Variable resolution discretization for high-accuracy solutions of optimal control problems
    • Rémi Munos and Andrew Moore. Variable resolution discretization for high-accuracy solutions of optimal control problems. In Proceedings IJCAI-99, 1999.
    • Proceedings IJCAI-99, 1999
    • Munos, R.1    Moore, A.2
  • 16
    • 0028497385 scopus 로고
    • An upper bound on the loss from approximate optimal-value functions
    • Satinder P. Singh and Richard C. Yee. An upper bound on the loss from approximate optimal-value functions. Machine Learning, 16:227-233, 1994.
    • (1994) Machine Learning , vol.16 , pp. 227-233
    • Singh, S.P.1    Yee, R.C.2
  • 17
    • 0004000699 scopus 로고    scopus 로고
    • Department of Electrical and Computer Engineering, University of Colorado at Boulder
    • Fabio Somenzi. CUDD: CU Decision Diagram Package Release 2.3.0. Department of Electrical and Computer Engineering, University of Colorado at Boulder, 1998.
    • (1998) CUDD: CU Decision Diagram Package Release 2.3.0
    • Somenzi, F.1
  • 18
    • 26944499565 scopus 로고    scopus 로고
    • APRICODD: Approximate policy construction using decision diagrams
    • Robert St-Aubin, Jesse Hoey, and Craig Boutilier. APRICODD: Approximate policy construction using decision diagrams. In Proceedings NIPS-2000, 2000.
    • (2000) Proceedings NIPS-2000
    • St-Aubin, R.1    Hoey, J.2    Boutilier, C.3
  • 19
    • 0029752470 scopus 로고    scopus 로고
    • Feature-based methods for large scale dynamic programming
    • John N. Tsitsiklis and Benjamin Van Roy. Feature-based methods for large scale dynamic programming. Machine Learning, 22:59-94, 1996.
    • (1996) Machine Learning , vol.22 , pp. 59-94
    • Tsitsiklis, J.N.1    Van Roy, B.2
  • 20
    • 0028460403 scopus 로고
    • Markov decision processes with impricise transition probabilities
    • Chelsea White and Hany Eldeib. Markov decision processes with impricise transition probabilities. Operations Research, 42(4), 1994.
    • (1994) Operations Research , vol.42 , Issue.4
    • White, C.1    Eldeib, H.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.