Milos Hauskrecht, Branislav Kveton  Home/Search
Context Related
| pitt.edu/~bkveton/docs/nips2003.pdf 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: pitt.edu/~bkveton/main (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Approximate linear programming (ALP) has emerged recently as one of the most promising methods for solving complex factored MDPs with finite state spaces. In this work we show that ALP solutions are not limited only to MDPs with finite state spaces, but that they can also be applied successfully to factored continuous-state MDPs (CMDPs). We show how one can build an ALP-based approximation for such a model and contrast it to existing solution methods. We argue that this approach offers a ... (Update)
Cited by: More
On the Smoothness of Linear Value Function Approximations - Branislav Kveton Intelligent (Correct)
Approximate Linear Programming for Solving - Hybrid Factored Mdps (Correct)
Planning In Hybrid Structured Stochastic - Domains Comenius University (Correct)
Active bibliography (related documents): More All
1.3: Linear Program Approximations for Factored Continuous-State .. - Hauskrecht, Kveton (2003) (Correct)
1.0: Heuristic Refinements of Approximate Linear Programming for .. - Kveton, Hauskrecht (2004) (Correct)
0.4: Solving Factored MDPs with Exponential-Family Transition Models - Kveton, Hauskrecht (2006) (Correct)
Similar documents based on text:
3.0: Unknown - (Correct)
Related documents from co-citation: More All
7: Generalized polynomial approximations in Markovian decision processes (context) - Schweitzer, Seidman - 1985
7: Solving factored MDPs with continuous and discrete variables - Guestrin, Hauskrecht et al. - 2004
6: Direct value-approximation for factored MDPs - Schuurmans, Patrascu - 2001
BibTeX entry: (Update)
Milos Hauskrecht and Branislav Kveton. Linear program approximations for factored continuousstate Markov decision processes. In Advances in Neural Information Processing Systems 16, pages 895--902, 2004. http://citeseer.ist.psu.edu/hauskrecht03linear.html More
@misc{ hauskrecht04linear,
author = "M. Hauskrecht and B. Kveton",
title = "Linear program approximations for factored continuousstate Markov decision
processes",
text = "Milos Hauskrecht and Branislav Kveton. Linear program approximations for
factored continuousstate Markov decision processes. In Advances in Neural
Information Processing Systems 16, pages 895--902, 2004.",
year = "2004",
url = "citeseer.ist.psu.edu/hauskrecht03linear.html" }
Citations (may not include all citations):614 Reinforcement Learning: An introduction - Sutton, Barto - 1998
413 Neuro-dynamic Programming (context) - Bertsekas, Tsitsiklis - 1996
291 Markov decision processes: discrete stochastic dynamic progr.. (context) - Puterman - 1994
278 Dynamic programming and optimal control (context) - Bertsekas - 1995
199 A model for reasoning about persistence and causation (context) - Dean, Kanazawa - 1989
42 Computing factored value functions for policies in structure.. - Koller, Parr - 1999
42 Max-norm projections for factored MDPs - Guestrin, Koller et al. - 2001
23 The Linear Programming Approach to Approximate Dynamic Progr.. - de Farias, Van Roy - 2003
21 Learning and value function approximation in complex decisio.. - Van Roy - 1998
20 Direct value-approximation for factored MDPs - Schuurmans, Patrascu - 2002
13 A counter-example to temporal differences learning - Bertsekas - 1994
9 A linear programming approach to solving stochastic dynamic .. - Trick, Zin - 1993
8 An optimal one-way multigrid algorithm for discretetime stoc.. (context) - Chow, Tsitsiklis - 1991
6 On constraint sampling for the linear programming approach t.. (context) - de Farias, Van Roy - 2001
6 Piecewise linear value function approximation for factored M.. - Poupart, Boutilier et al. - 2002
3 Using randomization to break the course of dimensionality (context) - Rust - 1997
3 Heuristics refinements of approximate linear programming for.. - Kveton, Hauskrecht - 2004
Documents on the same site (http://www.cs.pitt.edu/~bkveton/main.html): More
An MCMC Approach to Solving Hybrid Factored MDPs - Kveton, Hauskrecht (2005) (Correct)
Heuristic Refinements of Approximate Linear Programming for .. - Kveton, Hauskrecht (2004) (Correct)
Solving Factored MDPs with Exponential-Family Transition Models - Kveton, Hauskrecht (2006) (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