SOLUTION PROCEDURES FOR PARTIALLY OBSERVED MARKOV DECISION PROCESSES

The authors present three algorithms to solve the infinite horizon, expected discounted total reward partially observed Markov decision process (POMDP). Each algorithm integrates a successive approximations algorithm for the POMDP due to A. Smallwood and E. Sondik with an appropriately generalized numerical technique that has been shown to reduce CPU time until convergence for the completely observed case. The first technique is reward revision. The second technique is reward revision integrated with modified policy iteration. The third is a standard extrapolation. A numerical study indicates the potentially significant computational value of these algorithms.

• Corporate Authors:

  Operations Research Society of America

  Mount Royal and Guilford Avenue
  Baltimore, MD  United States  21202
• Authors:
  • WHITE III, C C
  • Scherer, W T
• Publication Date: 1989-9

Media Info

• Features: References; Tables;
• Pagination: p. 791-797
• Serial:
  • OPERATIONS RESEARCH
  • Volume: 37
  • Issue Number: 5
  • Publisher: NEWELL, GORDON F.

Subject/Index Terms

• TRT Terms: Algorithms; Decision making; Dynamic programming; Markov processes; Planning
• Subject Areas: Highways; Planning and Forecasting; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 00489584
• Record Type: Publication
• Files: TRIS
• Created Date: Nov 30 1989 12:00AM