@inproceedings{f41665a03bc74dcf8f19ea859d943f3f,
title = "Adaptive planning for markov decision processes with uncertain transition models via incremental feature dependency discovery",
abstract = "Solving large scale sequential decision making problems without prior knowledge of the state transition model is a key problem in the planning literature. One approach to tackle this problem is to learn the state transition model online using limited observed measurements. We present an adaptive function approximator (incremental Feature Dependency Discovery (iFDD)) that grows the set of features online to approximately represent the transition model. The approach leverages existing feature-dependencies to build a sparse representation of the state transition model. Theoretical analysis and numerical simulations in domains with state space sizes varying from thousands to millions are used to illustrate the benefit of using iFDD for incrementally building transition models in a planning framework.",
author = "Ure, \{N. Kemal\} and Alborz Geramifard and Girish Chowdhary and How, \{Jonathan P.\}",
year = "2012",
doi = "10.1007/978-3-642-33486-3\_7",
language = "English",
isbn = "9783642334856",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
number = "PART 2",
pages = "99--115",
booktitle = "Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2012, Proceedings",
address = "Germany",
edition = "PART 2",
note = "12th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2012 ; Conference date: 24-09-2012 Through 28-09-2012",
}