On policy iteration as a Newton's method and polynomial policy iteration algorithms

Proceedings of the National Conference on Artificial Intelligence

Volumn , Issue , 2002, Pages 273-278

  Madani, Omid ^a  

^a UNIVERSITY OF ALBERTA   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; ITERATIVE METHODS; LINEAR PROGRAMMING; MARKOV PROCESSES;

MARKOV DECISION PROCESSES (MDP);

DECISION MAKING;

EID: 0036927574     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. [BDH99] C. Boutilier, T. Dean, and S. Hanks. Decision theoretic planning: Structural assumptions and computational leverage. JAIR, pages 157-171, 1999.
2. [Ber95] D. P. Bertsekas. Dynamic Programming and Optimal Control. Athena Scientific, 1995.
3. [Con93] A. Condon. On algorithms for simple stochastic games. In Advances in computational complexity theory, volume 13 of DIMACS series in discrete mathematics and theoretical computer science. 1993.
4. [GKP01] C. Guestrin, D. Koller, and R. Parr. Max-norm projections for factored MDPs. In AAAI, pages 673-679, 2001.
5. [Han98] E. A. Hansen. Finite Memory Control of Partially Observable Systems. PhD thesis, U. of Mass., Amherst, 1998.
6. [HK66] A. Hoffman and R. Karp. On nonterminating stochastic games. Management Science, 12(5), 1966.
7. [HN94] D. S. Hochbaum and J. Naor. Simple and fast algorithms for linear and integer programs with two variables per inequality. SICOMP, 23(6):1179-1192, Dec 1994.
8. [HZ01] E. Hansen and S. Zilberstein. LAO*: a heuristic search algorithm that finds solutions with loops. Artificial Intelligence, 129:35-62, 2001.
9. [Kar78] R. M. Karp. A characterization of the minimum cycle mean in a digraph. Discrete Mathematics, 23:309-311, 1978.
10. [Lit96] M. Littman. Algorithms for Sequential Decision Making. PhD thesis, Brown, 1996.
11. [Mad00] O. Madani. Complexity Results for Infinite-Horizon Markov Decision Processes. PhD thesis, U. of Washington, 2000.
12. [Mad02] O. Madani. On policy iteration as a Newton's method and polynomial policy iteration algorithms. Technical report, U. of Alberta, 2002.
13. [MC94] M. Melekopoglou and A. Condon. On the complexity of the policy improvement algorithm for Markov decision processes. ORSA Journal on Computing, 6(2), 1994.
14. [Meg83] N. Megiddo. Towards a genuinely polynomial algorithm for linear programming. SICOMP, 12(2):347-353,1983.
15. [MS99] Y. Mansour and S. Singh. On the complexity of policy iteration. In Uncertainty in AI, pages 401-408, 1999.
16. [Rad92] T. Radzik. Newton's method for fractional combinatorial optimization. In 33rd FOCS, pages 659-669, 1992.
17. [RN95] S. Russell and P. Norvig. Artificial Intelligence: A Modern Approach. Prentice Hall, 1995.
18. [Sho81] R. Shostack. Deciding linear inequalities by computing loop residues. J. ACM, 28:769-779, 1981.
19. [Way99] K.D. Wayne. A polynomial combinatorial algorithm for generalized minimum cost flow. In 31st STOC, 1999.