A Cost-Shaping Linear Program for Average-Cost Approximate Dynamic Programming with Performance Guarantees

A Cost-Shaping Linear Program for Average-Cost Approximate Dynamic Programming with Performance Guarantees (2006)

Cached

Download Links

[www.stanford.edu]

by Daniela Pucci de Farias , Benjamin Van Roy

Citations:

7 - 2 self

BibTeX

@MISC{Farias06acost-shaping,
    author = {Daniela Pucci de Farias and Benjamin Van Roy},
    title = { A Cost-Shaping Linear Program for Average-Cost Approximate Dynamic Programming with Performance Guarantees},
    year = {2006}
}

Bookmark

OpenURL

Abstract

Citations

498	Markov Decision Processes - Puterman - 1994
223	Generalization in reinforcement learning: safely approximating the value function - Boyan, Moore - 1995
174	Near-optimal reinforcement learning in polynomial time - Kearns, Singh - 1998
172	Stable function approximation in dynamic programming - Gordon - 1995
105	The linear programming approach to approximate dynamic programming - Farias, Roy - 2003
99	Efficient solution algorithms for factored mdps - Guestrin, Koller, et al. - 2003
65	On constraint sampling in the linear programming approach to approximate dynamic programming - Farias, Roy
62	Approximate Solutions to Markov Decision Processes - Gordon - 1999
41	Error bounds for approximate policy iteration - Munos - 2003
33	Linear programming and sequential decisions - Manne - 1960
28	Value iteration and optimization of multiclass queueing networks. Queueing Systems Theory Appl - Chen, Meyn - 1999
28	A probabilistic production and inventory problem - D’Epenoux - 1963
26	Direct valueapproximation for factored MDPs - Schuurmans, Patrascu - 2001
24	A price-directed approach to stochastic inventory routing - Adelman
24	New linear program performance bounds for queueing networks - Morrison, Kumar - 1999
23	Spline approximations to value functions: A linear programming approach - Trick, Zin - 1997
22	Planning under uncertainty in complex structured environments - Guestrin - 2003
21	Solving factored MDPs with continuous and discrete variables - Guestrin, Hauskrecht, et al. - 2004
21	V.B.: Performance evaluation and policy selection in multiclass networks. Discrete Event Dyn - Henderson, Meyn, et al. - 2003
21	Feature-based methods for large-scale dynamic programming - Tsitsiklis, Roy - 1994
20	The policy iteration algorithm for average reward Markov decision processes with general state space - Meyn - 1997
19	Advantage updating applied to a differential game - Harmon, Baird, et al. - 1995
16	Criteria for uniform ergodicity and strong stability of Markov chains with a common phase space - Kartashov - 1984
13	Tetris: A study of randomized constraint sampling - Farias, Roy - 2006
13	Inequalities in theorems of ergodicity and stability for Markov chains with a common phase space - Kartashov - 1985
10	Convex analytic methods in Markov decision processes - Borkar - 2002
9	Workload models for stochastic networks: value functions and performance evaluation - Meyn - 2005
8	Approximate dynamic programming for networks: Fluid models and constraint reduction,” 2004, submitted for publication - Veatch
3	The linear programming approach - Hernández-Lerma, Lasserre - 2001
3	Generalized polynomial approximation in Markov decision processes - Schweitzer, Seidman - 1985
2	Approximate linear programming for average-cost dynamic programming - Farias, Roy - 2003