Omid Madani  Home/Search
Context Related
| cs.ualberta.ca/~madani/thesis.ps.gz 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: Complexity Results for In nite-Horizon Markov Decision Processes by Omid Madani Chair of Supervisory Committee Professor Richard Anderson Computer Science and Engineering Markov decision processes (MDPs) are models of dynamic decision making under uncertainty. These models arise in diverse applications and have been developed extensively in elds such as operations research, control engineering, and the decision sciences in general. Recent research, especially in arti cial intelligence,... (Update)
Context of citations to this paper: More
.... all POMDP problems have optimal finite controllers: a simple two state 2 armed bandit counter example can be constructed and see [20] for a 3 state UMDP counter example. In the next section, we will view action sequences as the desired output for solving UMDPs, but the...
...[Lit96] the well known local quadratic convergence results on Newton s method are not sufficient for proof of polynomial run time. In [Mad00] a bound is derived on the distance of each zero (x ) to the zero of the optimal gain function, which is shown to geometrically...
Cited by: More
On Policy Iteration as a Newton's Method and Polynomial.. - Algorithms Omid Madani (Correct)
On the Undecidability of Probabilistic Planning and Related.. - Madani, Hanks (2003) (Correct)
Active bibliography (related documents): More All
1.1: Algorithms for Partially Observable Markov Decision Processes - Zhang (2001) (Correct)
1.0: Computational Models for Decision Making in Dynamic and Uncertain .. - Madani (1998) (Correct)
0.7: Parallel Algorithms for the All-Sources Generalized Shortest.. - Oldham, Pratt (1999) (Correct)
Similar documents based on text: More All
0.4: Polynomial Value Iteration Algorithms for Deterministic MDPs - Omid Madani Department (2002) (Correct)
0.3: Resume - Madani (Correct)
0.2: On the Undecidability of Probabilistic Planning and.. - Madani, Hanks, Condon (1999) (Correct)
Related documents from co-citation: More All
2: Algorithms for Sequential Decision Making - Littman - 1996
2: Finite-Memory Control of Partially Observable Systems (context) - Hansen - 1998
2: Decision Theoretic Planning: Structural Assumptions and Computational Leverage - Boutilier, Dean et al.
BibTeX entry: (Update)
O. Madani. Complexity Results for Infinite-Horizon Markov Decision Processes. PhD thesis, University of Washington, 2000. http://citeseer.ist.psu.edu/madani00complexity.html More
@misc{ madani00complexity,
author = "O. Madani",
title = "Complexity Results for Infinite-Horizon Markov Decision Processes",
text = "O. Madani. Complexity Results for Infinite-Horizon Markov Decision Processes.
PhD thesis, University of Washington, 2000.",
year = "2000",
url = "citeseer.ist.psu.edu/madani00complexity.html" }
Citations (may not include all citations):3972 Introduction to algorithms (context) - Cormen, Leiserson et al. - 1992
1911 Introduction to Automata Theory (context) - Hopcroft, Ullman - 1979
951 Computational Complexity (context) - Papadimitriou - 1994
891 STRIPS: a new approach to the application of theorem proving.. (context) - Fikes, Nilsson - 1971
837 Cambridge University Press (context) - Motwani, Raghavan - 1995
717 Theory of Linear and Integer Programming (context) - Schrijver - 1986
482 Combinatorial Optimization: Algorithms and Complexity (context) - Papadimitriou, Steiglitz - 1998
408 Princeton University Press (context) - Bellman - 1957
370 Network Flows : Theory (context) - Ahuja, Magnanti et al. - 1993
278 Dynamic Programming and Optimal Control (context) - Bertsekas - 1995
246 Markov Decision Processes (context) - Puterman - 1994
230 Dynamic Programming: Deterministic and Stochastic Models (context) - Bertsekas - 1987
216 The Optimal Control of Partially Observable Markov Processes (context) - Sondik - 1971
216 The optimal control of partially observable Markov processes.. (context) - Smallwood, Sondik - 1973
216 The optimal control of partially observable Markov processes.. (context) - Sondik - 1978
188 Decision theoretic planning: Structural assumptions and comp.. - Boutilier, Dean et al. - 2000
185 Applying parallel computation algorithms in the design of se.. (context) - Megiddo - 1983
147 The computational complexity of propositional STRIPS plannin.. - Bylander - 1994
146 An algorithm for probabilistic planning - Kushmerick, Hanks et al. - 1995
106 A survey of partially observable Markov decision processes: .. (context) - Monahan - 1982
102 A characterization of the minimum cycle mean in a digraph (context) - Karp - 1978
96 The complexity of Markov decision processes (context) - Papadimitriou, Tsitsiklis - 1987
79 Stochastic games (context) - Shapley - 1953
76 Reinforcement Learning with Selective Perception and Hidden .. (context) - McCallum - 1995
73 Introduction to Probabilistic Automata (context) - Paz - 1971
64 decidability and undecidability results for domain-independe.. (context) - Erol, Nau et al. - 1995
64 Algorithms for Sequential Decision Making - Littman - 1996
53 Probabilistic propositional planning: Representations and co.. - Littman - 1997
53 A polynomial algorithm for linear programming (context) - Khachian - 1979
52 Information and Control (context) - Rabin - 1963
47 A survey of computational complexity results in systems and .. - Blondel, Tsitsiklis - 2000
46 The computational complexity of probabilistic planning - Littman, Goldsmith et al. - 1998
43 A subexponential randomized simplex algorithm (context) - Kalai - 1992
35 Exact and Approximate Algorithms for Partially Observable Ma.. (context) - Cassandra - 1998
32 Xavier: A robot navigation architecture based on partially o.. (context) - Koenig, Simmons - 1997
32 Simple and fast algorithms for linear and integer programs w.. (context) - Hochbaum, Naor - 1994
32 A survey of algorithmic methods for partially observable Mar.. (context) - Lovejoy - 1991
29 Policy iteration for factored MDPs - Koller, Parr - 2000
28 Finite Memory Control of Partially Observable Systems (context) - Hansen - 1998
26 the complexity of space bounded interactive proofs (context) - Condon, Lipton - 1989
26 Markov Decision Processes (context) - White - 1993
25 Tight bounds and 2-approximation algorithms for integer prog.. - Hochbaum, Megiddo et al. - 1993
24 Finding minimum cost to time ratio cycles with small integra.. (context) - Hartmann, Orlin - 1993
23 Probabilistic two way machines (context) - Freivalds - 1981
21 Towards a genuinely polynomial algorithm for linear programm.. (context) - Megiddo - 1983
19 Dynamic Programming: Models and Applications (context) - Denardo - 1982
19 the complexity of partially observed Markov decision process.. - Burago, De Rougemont et al. - 1996
19 Faster maximum and minimum mean cycle algorithms for systemp.. - Dasdan, Gupta - 1998
18 Parametric shortest path algorithms with an application to c.. (context) - Karp, Orlin - 1981
18 Observation of a Markov Process Through a Noisy Channel (context) - Drake - 1962
18 Improved algorithms for linear inequalities with two variabl.. (context) - Cohen, Megiddo - 1994
18 A polynomial time algorithm for solving systems of linear in.. (context) - Aspvall, Shiloach - 1980
17 On nonterminating stochastic games (context) - Ho, Karp - 1966
16 Finite State Markov Decision Processes (context) - Derman - 1970
15 Active gesture recognition using partially observable Markov.. - Darrell, Pentland - 1996
15 Optimal control of markov processes with incomplete state in.. (context) - Astrom - 1965
13 A subexponential randomized algorithm for the simple stochas.. (context) - Ludwig - 1995
12 Linear programming with two variables per inequality in poly.. - Lueker, Megiddo et al. - 1990
12 Sensors For Mobile Robots (context) - Everett - 1995
11 A polynomial combinatorial algorithm for generalized minimum.. - Wayne - 1999
11 An improved policy iteration algorithm for partially observa.. - Hansen - 1998
10 Complexity issues in Markov decision processes - Goldsmith, Mundhenk - 1998
9 Theoretical properties of the network simplex method (context) - Cunningham - 1979
8 Robot navigation with Markov models: a framework for path pl.. (context) - Koenig, Goodwin et al. - 1995
8 Newton's method for fractional combinatorial optimization (context) - Radzik - 1992
8 Finding minimum-cost circulations by cancelling negative cyc.. (context) - Goldberg, Tarjan - 1989
8 Distinguishing tests for nondeterministic and probabilistic .. - Alur, Couroubetis et al. - 1995
8 Planning medical therapy using partially observable Markov d.. (context) - Hauskrecht, Fraser - 1998
8 Mathematics of Operations Research (context) - Klee, Kleinschmidt et al. - 1987
7 Polyhedral sets having a least element (context) - Cottle, Veinott - 1972
7 the complexity of the policy improvement algorithm for Marko.. - Melekopoglou, Condon - 1994
7 Parametric approaches to fractional programs (context) - Ibaraki - 1983
7 On algorithms for simple stochastic games - Condon - 1993
6 Further real applications of Markov decision processes (context) - White - 1988
6 The complexity of policy existence problem for partially-obs.. (context) - Mundhenk, Goldsmith et al. - 1997
5 Testing the necklace condition for shortest tours and optima.. (context) - Edelsbrunner, Rote et al. - 1989
5 The complexity of simple stochastic games (context) - Condon - 1992
5 Multichain markov renewal programs (context) - Denardo, Fox - 1968
5 The analytic theory of policy iteration (context) - Puterman, Brumelle - 1978
5 horizon stationary Markov decision process in time proportio.. (context) - Tseng - 1990
4 A survey of maintenance models: The control and surveillance.. (context) - Pierskalla, Voelker - 1976
4 What is the worst case behavior of the simplex algorithm (context) - Zadeh - 1980
4 Numerical computation of spectral elements in max-plus algeb.. (context) - Cochet-Terrasson, Cohen et al. - 1998
4 Deciding linear inequalities by computing loop residues (context) - Shostack - 1981
4 Arti cial Intelligence Research (context) - Kaelbling, Littman et al. - 1996
4 Dynamic Programming and Markov Decision Processes (context) - Howard - 1960
4 Fractional combinatorial optimization (context) - Radzik - 1998
3 Complexity results for nite-horizon markov decision processs.. (context) - Mundhenk, Goldsmith et al. - 2000
3 The Stable Marriage Problem (context) - eld, Irving - 1989
3 Optimal control of partially observable Markovian systems (context) - Aoki - 1965
3 The Hirsch conjecture in Leontief substitution systems (context) - Grinold - 1970
3 Algorithms for stochastic games with geometrical interpretat.. (context) - Pollatschek, Avi-Itzhak - 1969
3 the complexity of policy iteration - Mansour, Singh - 1999
3 Parametric cost shortest path problems (context) - Carstensen - 1984
3 Mathematics of Operations Research (context) - Piasaruk, cyclical - 1999
2 Computational comparison of value iteration algorithms for d.. (context) - Thomas, Hartley et al. - 1983
2 Inspection models and their applications (context) - Thomas, Gaver et al. - 1991
2 The complexity of policy evaluation for nite-horizon partial.. (context) - Mundhenk, Goldsmith et al. - 1997
2 Uber eine neue au osungsart der bei der methode der kleinst.. (context) - Jacobi - 1945
2 An algorithm for fractional assignment problems - Shigeno, Saruwatari et al. - 1995
2 On minimal mean cuts and circuits in a digraph (context) - Karzanov - 1985
2 New algorithms for generalized network ows (context) - Cohen, Megiddo - 1994
2 Finding minimal cost-time ratio circuits (context) - Fox - 1969
2 Parametric combinatorial computing and a problem of program .. (context) - eld - 1983
2 the computability of in nite-horizon partially observable Ma.. (context) - Madani, Hanks et al. - 1999
2 World Scienti c (context) - Bellman, the et al. - 1984
2 Incremental pruning: A simple fast exact algorithm for parti.. (context) - Cassandra, Littman et al. - 1997
2 Uncertainty and real-time therapy planning: Incremental Mark.. - Washington - 1996
1 Representation of general and polyhedral sublattices of prod.. (context) - Jr - 1989
1 Sucient statistics in the optimum control of stochastic syst.. (context) - Striebel - 1965
1 the maximum operation and monotone convergence (context) - Kalaba, di and et al. - 1959
1 On constraints on the search path of policy iteration - Madani - 1998
1 Computational comparison of policy iteration algorithms for .. (context) - Hartley, Lavercombe et al. - 1986
1 the complexity of the policy iteration algorithm (context) - Melekopoglou, Condon - 1990
1 The complexity of some problems in parametric linear and com.. (context) - Cartstensen - 1983
1 Ecient algorithms for certain satis ability and linear progr.. (context) - Aspvall - 1980
1 Combinatorial algorithms for generalized ow problems (context) - Oldham - 1999
1 Cahiers du Centre de Recherche Operationelle (context) - DeGhellinck, ems et al. - 1960
1 Solving the minimum-cost ow problem by successive approximat.. (context) - Goldberg, Tarjan - 1990
1 Minimizing capacity violations in a transshipment network (context) - Radzik - 1992
1 Sur un probleme de production et de stockage dans l'aleato.. (context) - D'Epenoux - 1963
1 A partially observed model of decision making by sherman (context) - Lane - 1989
1 Partially Observable Markov Decision Process Models for Stru.. (context) - Jiang - 1994
1 Ecient algorithms for optimal cycle mean and optimum cost to.. (context) - Dasdan, Irani et al. - 1999
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