Computer Science – Artificial Intelligence
Scientific paper
2010-05-11
Computer Science
Artificial Intelligence
Technical report corresponding to the ICML2010 submission of the same name
Scientific paper
Approximate dynamic programming has been used successfully in a large variety of domains, but it relies on a small set of provided approximation features to calculate solutions reliably. Large and rich sets of features can cause existing algorithms to overfit because of a limited number of samples. We address this shortcoming using $L_1$ regularization in approximate linear programming. Because the proposed method can automatically select the appropriate richness of features, its performance does not degrade with an increasing number of features. These results rely on new and stronger sampling bounds for regularized approximate linear programs. We also propose a computationally efficient homotopy method. The empirical evaluation of the approach shows that the proposed method performs well on simple MDPs and standard benchmark problems.
Parr Ron
Petrik Marek
Taylor Gavin
Zilberstein Shlomo
No associations
LandOfFree
Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-384987