Sign up & Download
Sign in

ACTION-BASED REPRESENTATION DISCOVERY IN MARKOV DECISION PROCESSES

by Sarah Osentoski
Access (2009)

Abstract

Approaches for representation discovery in (S)MDPs using basis functions, function approximation techniques. Shows that these perform better than traditional hand-crafted approaches. Examined automatic building basis function representations by explicitly incorporating actions and doing this for hierarchical RL as well. State-action representations were shown to outperform state representations as it can simultaneously generalize over states and actions. Method proceeds by building graphs of transitions in the domain, and performing spectral analysis on these graphs. This captures the underlying structure of the domain. Also uses pre-defined task hierarchies.

Cite this document (BETA)

Available from www-anw.cs.umass.edu
Page 1
hidden

ACTION-BASED REPRESENTATION DISCOVERY IN MARKOV DECISION PROCESSES

University of Massachusetts - Amherst
ScholarWorks@UMass Amherst
Open Access Dissertations Dissertations and Theses
9-1-2009
Action-based representation discovery in markov
decision processes
Sarah Osentoski
University of Massachusetts - Amherst, sosentos@cs.umass.edu
This Dissertation is brought to you for free and open access by the Dissertations and Theses at ScholarWorks@UMass Amherst. It has been accepted
for inclusion in Open Access Dissertations by an authorized administrator of ScholarWorks@UMass Amherst. For more information, please contact
scholarworks@library.umass.edu.
Recommended Citation
Osentoski, Sarah, "Action-based representation discovery in markov decision processes" (2009). Open Access Dissertations. Paper 119.
http://scholarworks.umass.edu/open_access_dissertations/119
Page 2
hidden
ACTION-BASED REPRESENTATION DISCOVERY IN MARKOV
DECISION PROCESSES
A Dissertation Presented
by
SARAH OSENTOSKI
Submitted to the Graduate School of the
University of Massachusetts Amherst in partial fulfillment
of the requirements for the degree of
DOCTOR OF PHILOSOPHY
September 2009
Department of Computer Science

Sign up today - FREE

Mendeley saves you time finding and organizing research. Learn more

  • All your research in one place
  • Add and import papers easily
  • Access it anywhere, anytime

Start using Mendeley in seconds!

Already have an account? Sign in

Readership Statistics

5 Readers on Mendeley
by Discipline
 
 
by Academic Status
 
100% Ph.D. Student
by Country
 
40% United States
 
40% United Kingdom
 
20% Japan