Bounding the suboptimality of reusing subproblems

IJCAI International Joint Conference on Artificial Intelligence

Volumn 2, Issue , 1999, Pages 1340-1345

  Bowling, Michael ^a   Veloso, Manuela ^a  

^a Carnegie Mellon University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACTION SELECTION; BELLMAN ERROR; COURSE OF ACTION; LEARNING SPEED; MARKOV DECISION PROCESSES; OPTIMAL POLICIES; PROBLEM DECOMPOSITION; SUBOPTIMALITY;

ARTIFICIAL INTELLIGENCE; MARKOV PROCESSES;

OPTIMIZATION;

EID: 84880690842     PISSN: 10450823     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. D. P. Bertsekas. Dynamic Programming: Deterministic and Stochastic Models. Prentice-Hall, En-glewood Cliffs, NJ, 1987.
2. T. Dean and S.-H. Lin. Decomposition techniques for planning in stochastic domains. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (IJCAI-95), 1995.
3. M. Hauskrecht, N. Meuleau, L. P. Kaelbling, T. Dean, and C. Boutilier. Hierarchical solution of markove decision processes using macro-actions. In Proceedings of the Fourteenth Annual Conference on Uncertainty in Artificial Intelligence (UAI-98), 1998.
4. L. P. Kaelbling, M. L. Littman, and A. W. Moore. Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4:237-285,1996.
5. R. Parr. Flexible decomposition algorithms for weakly coupled markov decision problems. In Proceedings of the Fourteenth Annual Conference on Uncertainty in Artificial Intelligence (UAI-98), 1998.
6. R. Sutton, D. Precup, and S. Singh. Between MDPs and semi-MDPs: Learning, planning, and representing knowledge at multiple temporal scales. Tech-nical report, Department of Computer Science, University of Massachusets, Amherst, 1998.
7. S. Thrun and A. Schwartz. Finding structure in reinforcement learning. In G. Tesauro, D. Touretzky, and T. Leen, editors, Advances in Neural Information Processing Systems, volume 7, pages 385-392. The MIT Press, 1995.
8. M. M. Veloso. Flexible strategy learning: Analogical replay of problem solving episodes. In Proceedings of AAAI-94, the Twelfth National Conference on Artificial Intelligence, pages 595-600, Seattle, WA, August 1994. AAAI Press.
9. Christopher J. C. H. Watkins. Learning from Delayed Rewards. PhD thesis, King's College, Cambridge, UK, 1989.
10. R. J. Williams and L. C. Baird. Tight performance bounds on greedy policies based on imperfect value functions. Technical report, College of Computer Science, Northeastern University, 1993.