(Enter summary)
Abstract: Markov Decision Processes (MDPs) provide a coherent
mathematical framework for planning under uncertainty.
However, exact MDP solution algorithms require the manipulation
of a value function, which specifies a value for
each state in the system. Most real-world MDPs are too
large for such a representation to be feasible, preventing the
use of exact MDP algorithms. Various approximate solution
algorithms have been proposed, many of which use a
linear combination of basis functions to... (Update)
Cited by: More
Monte-Carlo optimizations for resource allocation problems .. - Network Systems Milos
(Correct)
Approximate Linear Programming for Solving - Hybrid Factored Mdps
(Correct)
Planning In Hybrid Structured Stochastic - Domains Comenius University
(Correct)
Similar documents (at the sentence level): More
45.3%: Max-norm Projections for Factored MDPs - Guestrin, Koller, Parr (2001)
(Correct)
34.6%: International Joint Conference on Artificial.. - Max-Norm Projections For (2001)
(Correct)
5.9%: Solving Factored POMDPs with Linear Value Functions - Guestrin, Koller, Parr (2001)
(Correct)
Active bibliography (related documents): More All
0.0: Value-Function Approximations for Partially Observable Markov.. - Hauskrecht (2000)
(Correct)
0.0: Reinforcement Learning: A Survey - Kaelbling, Littman, Moore (1996)
(Correct)
0.0: Generalized Markov Decision Processes.. - Szepesvári.. (1996)
(Correct)
Similar documents based on text: More All
1.0: Multiagent Planning with Factored MDPs - Guestrin, Koller, Parr (2001)
(Correct)
0.7: Context Specific Multiagent Coordination and Planning.. - Guestrin, Venkataraman (2002)
(Correct)
0.6: Context-Specific Multiagent Coordination and Planning .. - Guestrin.. (2002)
(Correct)
Related documents from co-citation: More All
22: Computing factored value functions for policies in structured MDPs
- Koller, Parr - 1999
21: A model for reasoning about persistence and causation (context) - Dean, Kanazawa - 1989
21: Neuro-Dynamic Programming (context) - Bertsekas, Tsitsiklis - 1996
BibTeX entry: (Update)
Carlos Guestrin, Daphne Koller, and Ronald Parr. Max-norm projections for factored MDPs. In Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI-01), Seattle, Washington, August 2001. Morgan Kaufmann. http://citeseer.ist.psu.edu/article/guestrin01maxnorm.html More
@inproceedings{ guestrin01maxnorm,
author = "Carlos Guestrin and Daphne Koller and Ronald Parr",
title = "Max-norm Projections for Factored {MDPs}",
booktitle = "{IJCAI}",
pages = "673-682",
year = "2001",
url = "citeseer.ist.psu.edu/article/guestrin01maxnorm.html" }
Citations (may not include all citations):
782
Artificial Intelligence: A Modern Approach (context) - Russell, Norvig - 1994
199
A model for reasoning about persistence and causation (context) - Dean, Kanazawa - 1989
188
Decision theoretic planning: Structural assumptions and comp..
- Boutilier, Dean et al. - 1999
130
Influence diagrams (context) - Howard, Matheson - 1984
95
Bucket elimination: A unifying framework for reasoning
- Dechter - 1999
59
Feature-based methods for large scale dynamic programming
- Tsitsiklis, Van Roy - 1996
53
Tight performance bounds on greedy policies based on imperfe..
- Williams, Baird - 1993
7
Chelsea Publishing Co (context) - Cheney - 1982
5
linear programming and tchebycheff approximation (context) - Stiefel, jordan - 1960
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