View in EDS

Partially Observable Markov Decision Processes Over an Infinite Planning Horizon with Discounting. Technical Report No. 77.

Saved in:
Bibliographic Details
Title: Partially Observable Markov Decision Processes Over an Infinite Planning Horizon with Discounting. Technical Report No. 77.
Authors: Wollmer, Richard D., University of Southern California, Los Angeles. Behavioral Technology Labs.
Peer Reviewed: N
Page Count: 25
Publication Date: 1976
Sponsoring Agency: Advanced Research Projects Agency (DOD), Washington, DC.
Office of Naval Research, Arlington, VA. Personnel and Training Research Programs Office.
Document Type: Reports - Descriptive
Descriptors: Computer Assisted Instruction, Decision Making, Instructional Systems, Linear Programing, Mathematical Applications, Mathematical Models, Operations Research, Probability, Systems Approach
Abstract: The true state of the system described here is characterized by a probability vector. At each stage of the system an action must be chosen from a finite set of actions. Each possible action yields an expected reward, transforms the system to a new state in accordance with a Markov transition matrix, and yields an observable outcome. The problem of finding the total maximum discounted reward as a function of the probability state vector may be formulated as a linear program with an infinite number of constraints. The reward function may be expressed as a partial N-dimensional Maclaurin series. The coefficients in this series are also determined as an optimal solution to a linear program with an infinite number of constraints. A sequence of related finitely constrained linear programs is solved which then generates a sequence of solutions that converge to a local minimum for the infinitely constrained program. This model is applicable to computer assisted instruction systems as well as to other situations. (Author/CH)
Entry Date: 1976
Accession Number: ED124161
Database: ERIC
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://eric.ed.gov/contentdelivery/servlet/ERICServlet?accno=ED124161
    Name: ERIC Full Text
    Category: fullText
    Text: Full Text from ERIC
Header DbId: eric
DbLabel: ERIC
An: ED124161
AccessLevel: 3
PubType: Report
PubTypeId: report
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Partially Observable Markov Decision Processes Over an Infinite Planning Horizon with Discounting. Technical Report No. 77.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Wollmer%2C+Richard+D%2E%22">Wollmer, Richard D.</searchLink><br /><searchLink fieldCode="AR" term="%22University+of+Southern+California%2C+Los+Angeles%2E+Behavioral+Technology+Labs%2E%22">University of Southern California, Los Angeles. Behavioral Technology Labs.</searchLink>
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: N
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 25
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 1976
– Name: SourceSuprt
  Label: Sponsoring Agency
  Group: SrcSuprt
  Data: Advanced Research Projects Agency (DOD), Washington, DC.<br />Office of Naval Research, Arlington, VA. Personnel and Training Research Programs Office.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Reports - Descriptive
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Computer+Assisted+Instruction%22">Computer Assisted Instruction</searchLink><br /><searchLink fieldCode="DE" term="%22Decision+Making%22">Decision Making</searchLink><br /><searchLink fieldCode="DE" term="%22Instructional+Systems%22">Instructional Systems</searchLink><br /><searchLink fieldCode="DE" term="%22Linear+Programing%22">Linear Programing</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+Applications%22">Mathematical Applications</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+Models%22">Mathematical Models</searchLink><br /><searchLink fieldCode="DE" term="%22Operations+Research%22">Operations Research</searchLink><br /><searchLink fieldCode="DE" term="%22Probability%22">Probability</searchLink><br /><searchLink fieldCode="DE" term="%22Systems+Approach%22">Systems Approach</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The true state of the system described here is characterized by a probability vector. At each stage of the system an action must be chosen from a finite set of actions. Each possible action yields an expected reward, transforms the system to a new state in accordance with a Markov transition matrix, and yields an observable outcome. The problem of finding the total maximum discounted reward as a function of the probability state vector may be formulated as a linear program with an infinite number of constraints. The reward function may be expressed as a partial N-dimensional Maclaurin series. The coefficients in this series are also determined as an optimal solution to a linear program with an infinite number of constraints. A sequence of related finitely constrained linear programs is solved which then generates a sequence of solutions that converge to a local minimum for the infinitely constrained program. This model is applicable to computer assisted instruction systems as well as to other situations. (Author/CH)
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 1976
– Name: AN
  Label: Accession Number
  Group: ID
  Data: ED124161
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=ED124161
RecordInfo BibRecord:
  BibEntity:
    PhysicalDescription:
      Pagination:
        PageCount: 25
    Subjects:
      – SubjectFull: Computer Assisted Instruction
        Type: general
      – SubjectFull: Decision Making
        Type: general
      – SubjectFull: Instructional Systems
        Type: general
      – SubjectFull: Linear Programing
        Type: general
      – SubjectFull: Mathematical Applications
        Type: general
      – SubjectFull: Mathematical Models
        Type: general
      – SubjectFull: Operations Research
        Type: general
      – SubjectFull: Probability
        Type: general
      – SubjectFull: Systems Approach
        Type: general
    Titles:
      – TitleFull: Partially Observable Markov Decision Processes Over an Infinite Planning Horizon with Discounting. Technical Report No. 77.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: University of Southern California, Los Angeles. Behavioral Technology Labs.
      – PersonEntity:
          Name:
            NameFull: Wollmer, Richard D.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 03
              Type: published
              Y: 1976
ResultId 1