Title
Tractable Pomdp Representations For Intelligent Tutoring Systems
Keywords
Computer-based training; Intelligent tutoring systems; Partially observable Markov decision processes
Abstract
With Partially Observable Markov Decision Processes (POMDPs), Intelligent Tutoring Systems (ITSs) can model individual learners from limited evidence and plan ahead despite uncertainty. However, POMDPs need appropriate representations to become tractable in ITSs that model many learner features, such as mastery of individual skills or the presence of specific misconceptions. This article describes two POMDP representations-state queues and observation chains-that take advantage of ITS task properties and let POMDPs scale to represent over 100 independent learner features. A real-world military training problem is given as one example. A human study (n = 14) provides initial validation for the model construction. Finally, evaluating the experimental representations with simulated students helps predict their impact on ITS performance. The compressed representations can model a wide range of simulated problems with instructional efficacy equal to lossless representations. With improved tractability, POMDP ITSs can accommodate more numerous or more detailed learner states and inputs. © 2013 ACM.
Publication Date
3-1-2013
Publication Title
ACM Transactions on Intelligent Systems and Technology
Volume
4
Issue
2
Number of Pages
-
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1145/2438653.2438664
Copyright Status
Unknown
Socpus ID
84876121023 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84876121023
STARS Citation
Folsom-Kovarik, Jeremiah T.; Sukthankar, Gita; and Schatz, Sae, "Tractable Pomdp Representations For Intelligent Tutoring Systems" (2013). Scopus Export 2010-2014. 6722.
https://stars.library.ucf.edu/scopus2010/6722