Omid Madani Department of Computing Science University of Alberta Edmonton,...  Home/Search
Context Related
| cs.ualberta.ca/~madan...valueitrFull.ps Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: cs.ualberta.ca/~madani...research (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Value iteration is a commonly used and an empirically competitive method in solving many Markov decision process problems. However, it is known that value iteration has only pseudopolynomial complexity in general. We establish a somewhat surprising polynomial bound for value iteration on deterministic Markov decision (DMDP) problems. We show that the basic value iteration procedure converges to the highest average reward cycle on a DMDP problem in (n iterations, or (mn ) total... (Update)
Context of citations to this paper: More
...given proofs sketches for the important steps. Complete proofs with more explanations and an expanded empirical section appear in [Mad02b]. 2 Preliminaries We give the graph theoretic definition of the DMDP problem here to save space. Let G = V; E; r) be a directed graph...
Cited by: More
Polynomial Value Iteration Algorithms for Deterministic MDPs - Madani (2002) (Correct)
Active bibliography (related documents): More All
0.4: Complexity results for Infinite-Horizon Markov Decision Processes - Madani (2000) (Correct)
0.2: On the Undecidability of Probabilistic Planning and.. - Madani, Hanks, Condon (2003) (Correct)
0.2: Timing Analysis of Embedded Real-Time Systems - Dasdan (1999) (Correct)
Similar documents based on text: More All
0.6: On Policy Iteration as a Newton's Method and Polynomial.. - Algorithms Omid Madani (Correct)
0.4: Resume - Madani (Correct)
0.3: On the Undecidability of Probabilistic Planning and.. - Madani, Hanks, Condon (1999) (Correct)
BibTeX entry: (Update)
O. Madani. Polynomial value iteration algorithms for deterministic mdps. Technical report, University of Alberta, 2002. Available at www.cs.ualberta.ca/ madani/valueitrFull.ps. http://citeseer.ist.psu.edu/madani02polynomial.html More
@misc{ madani02polynomial,
author = "O. Madani",
title = "Polynomial value iteration algorithms for deterministic mdps",
text = "O. Madani. Polynomial value iteration algorithms for deterministic mdps.
Technical report, University of Alberta, 2002. Available at www.cs.ualberta.ca/
madani/valueitrFull.ps.",
year = "2002",
url = "citeseer.ist.psu.edu/madani02polynomial.html" }
Citations (may not include all citations):3972 Introduction to algorithms (context) - Cormen, Leiserson et al. - 1998
370 Network Flows : Theory (context) - Ahuja, Magnanti et al. - 1993
250 Artificial Intelligence:A Modern Approach (context) - Russell, Norvig - 1995
246 Markov Decision Processes (context) - Puterman - 1994
188 Decision theoretic planning: Structural assumptions and comp.. - Boutilier, Dean et al. - 1999
102 A characterization of the minimum cycle mean in a digraph (context) - Karp - 1978
79 Stochastic games (context) - Shapley - 1953
64 Algorithms for Sequential Decision Making - Littman - 1996
42 Max-norm projections for factored MDPs - Guestrin, Koller et al. - 2001
28 Finite Memory Control of Partially Observable Systems (context) - Hansen - 1998
24 Finding minimum cost to time ratio cycles with small integra.. (context) - Hartmann, Orlin - 1993
23 Faster parametric shortest paths and minimum balance algorit.. - Young, Tarjan et al. - 1991
19 Faster maximum and minimum mean cycle algorithms for systemp.. - Dasdan, Gupta - 1998
18 Parametric shortest paths algorithm with an application to c.. (context) - Karp, Orlin - 1981
9 The complexity of mean payoff games on graphs - Zwick, Paterson
5 horizon stationary Markov decision process in time proportio.. (context) - Tseng - 1990
2 On policy iteration as a Newton's method and polynomial poli.. (context) - Madani - 2002
Documents on the same site (http://www.cs.ualberta.ca/~madani/research.html): More
Polynomial Value Iteration Algorithms for Deterministic MDPs - Madani (2002) (Correct)
On the Undecidability of Probabilistic Planning and.. - Madani, Hanks, Condon (2003) (Correct)
On Policy Iteration as a Newton's Method and Polynomial.. - Algorithms Omid Madani (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC