2010
DOI: 10.1007/978-3-642-11688-9_3
View full text |Buy / Rent full text
|
Sign up to set email alerts
|

Abstract: This chapter presents and evaluates an on-line representation selection method for factored MDPs. The method addresses a special case of the feature selection problem that only considers certain sub-sets of features, which we call candidate representations. A motivation for the method is that it can potentially deal with problems where other structure learning algorithms are infeasible due to a large degree of the associated dynamic Bayesian network (DBN). Our method uses switch actions to select a representat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2013
2013
2018
2018

Publication Types

Select...
3
1
1

Relationship

1
4

Authors

Journals

citations
Cited by 7 publications
(8 citation statements)
references
References 9 publications
(8 reference statements)
0
5
0
Order By: Relevance
“…Although similar methods have also been applied to transfer learning, most of these learn task-relevant representations for SL [2,5] or RL [18,30,37,40,60,70,75,83]; the latter aim to reduce the state space of the target task, or find good representations for value functions or policies. However, none of these approaches learn domain-relevant representations.…”
Section: Representation Learningmentioning
confidence: 99%
“…Although similar methods have also been applied to transfer learning, most of these learn task-relevant representations for SL [2,5] or RL [18,30,37,40,60,70,75,83]; the latter aim to reduce the state space of the target task, or find good representations for value functions or policies. However, none of these approaches learn domain-relevant representations.…”
Section: Representation Learningmentioning
confidence: 99%
“…This problem is a modified version of the scenario discussed in [22], which is a stochastic task. There is a crossroad with two-way road resulting in a four-square grid at the center, a horizontal and a vertical one.…”
Section: Case Studies and Resultsmentioning
confidence: 99%
“…7 The goal is similar to that of earlier work by Jonsson and Barto (2002) in which each option implemented a separate instance of McCallum's (1996) U-Tree algorithm designed to synthesize state representations from past histories of observations and actions. The goal is also similar to that of Seijen et al (2007) who studied a method that included special abstraction-switching actions.…”
Section: Selecting Skill-specific Abstractionsmentioning
confidence: 97%