Proceedings of the Sixteenth International Joint Conference on Artificial...  Home/Search
Context Related
| stanford.edu/people/daph...ijcai99kp.ps Cached: 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.
PS.gz PS Image Update HelpFrom: stanford.edu/people/d...ijcai99kp (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Many large Markov decision processes (MDPs) can be represented compactly using a structured representation such as a dynamic Bayesian network. Unfortunately, the compact representation does not help standard MDP algorithms, because the value function for the MDP does not retain the structure of the process description. We argue that in many such MDPs, structure is approximately retained. That is, the value functions are nearly additive: closely approximated by a linear function over... (Update)
Similar documents based on text: More All
0.5: Max-norm Projections for Factored MDPs - Guestrin, Koller, Parr (2001) (Correct)
0.4: Policy Iteration for Factored MDPs - Koller, Parr (2000) (Correct)
0.4: Computing factored value functions for policies in structured.. - Koller, Parr (1999) (Correct)
BibTeX entry: (Update)
D. Koller and R. Parr. Computing factored value functions for policies in structured MDPs. In Proc. IJCAI99. Morgan Kaufmann, 1999. http://citeseer.ist.psu.edu/article/koller99computing.html More
@inproceedings{ koller99computing,
author = "Daphne Koller and Ronald Parr",
title = "Computing Factored Value Functions for Policies in Structured {MDPs}",
booktitle = "{IJCAI}",
pages = "1332-1339",
year = "1999",
url = "citeseer.ist.psu.edu/article/koller99computing.html" }
Citations (may not include all citations):259 Decisions with Multiple Objectives: Preferences and Value Tr.. (context) - Keeney, Raiffa - 1976
196 Linear Algebra and Its Applications (context) - Strang - 1980
188 Decision theoretic planning: Structural assumptions and comp.. - Boutilier, Dean et al. - 1999
130 Influence diagrams (context) - Howard, Matheson - 1984
113 Tractable inference for complex stochastic processes - Boyen, Koller - 1998
66 Stable function approximation in dynamic programming - Gordon - 1995
59 Feature-based methods for large scale dynamic programming - Tsitsiklis, Van Roy - 1996
34 Solving very large weakly coupled Markov decision processes - Meuleau, Hauskrecht et al. - 1998
30 Approximating value trees in structured dynamic programming - Boutilier, Dearden - 1996
28 Graphical models for preference and utility - Bacchus, Grove - 1995
24 Model reduction techniques for computing approximately optim.. - Dean, Givan et al. - 1997
23 How to dynamically merge Markov decision processes - Singh, Cohn - 1998
21 Learning and Value Function Approximation in Complex Decisio.. - Van Roy - 1998
20 Scaling up average reward reinforcement learning by approxim.. - Tadepalli, Ok - 1996
12 Prioritized goal decomposition of Markov decision processes:.. - Boutilier, Brafman et al. - 1998
[Article contains additional citations not shown here]
The graph only includes citing articles where the year of publication is known.
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