[an error occurred while processing this directive]

CompSci 295 Planning as Inference, Fall 2013

  • Classroom: DBH 1425
  • Day: Wednesday
  • Time: 3:00 - 4:50p
  • Instructor: Rina Dechter - dechter@ics.uci.edu

This seminar will focus on planning as inference.

Relevant sources:

  • A Concise Introdudction to Models and Methods for Automated Planning
    Hector Geffner and Blai Bonet
  • Decision-Theoretic Planning: Structural Assumptions and Computational Leverage
    Craig Boutilier, Thomas Dean, and Steve Hanks
    Journal of Artificial Intelligence Research, 1999
  • List of Accepted Papers at ICAPS 2013
  • ICAPS Proceedings
  • Papers by Carmel Domshlak
    • To UCT, or not to UCT? (Position Paper) [pdf]
      Carmel Domshlak, Zohar Feldman
      SOCS-13. 6th Annual Symposium on Combinatorial Search, Leavenworth, WA, USA, July 2013.

    • Monte-Carlo Planning: Theoretically Fast Convergence Meets Practical Efficiency [pdf]
      Zohar Feldman, Carmel Domshlak
      UAI-13. 29th Conference on Uncertainty in Artificial Intelligence, Bellevue, WA, USA, July 2013.

    • Fault tolerant contingent planning: Complexity and compilation [pdf]
      Carmel Domshlak
      ICAPS-13. 23nd International Conference on Automated Planning and Scheduling, Rome, Italy, June 2013.

    • Planning for Operational Control Systems with Predictable Exogenous Events
      Ronen Brafman, Carmel Domshlak, Yagil Engel, and Zohar Feldman
      AAAI-11, 25th AAAI Conference on Artificial Intelligence, San-Francisco, CA, USA, August 2010.

    • Probabilistic Planning via Heuristic Forward Search and Weighted Model Counting [abstract, pdf]
      Carmel Domshlak, Joerg Hoffmann
      Journal of Artificial Intelligence Research, volume 30, pp 565-620, 2007.

      • Fast Probabilistic Planning Through Weighted Model Counting [pdf, slides]
        Carmel Domshlak, Joerg Hoffmann
        ICAPS-06. 16th International Conference on Automated Planning and Scheduling, pp 243-252, The English Lake District, U.K., September 2006.

  • Marc Toussaint Papers

    • Probabilistic inference for solving (PO)MDPs [pdf]
      Marc Toussaint, Stefan Harmeling, and Amos Storkey
      Technical Report EDI-INF-RR-0934, University of Edinburgh, School of Informatics, 2006.

    • Nice applications that demonstrate efficiency in challenging domains are:

      • Hierarchical POMDP Controller Optimization by Likelihood Maximization [pdf]
        Marc Toussaint, Laurent Charlin, and Pascal Poupart
        In Uncertainty in Artificial Intelligence (UAI 2008), 562-570, AUAI Press, 2008.

      • Scalable Multiagent Planning Using Probabilistic Inference [pdf]
        Akshat Kumar, Shlomo Zilberstein, and Marc Toussaint
        In Proc. of the 22nd Int. Joint Conf. on Artificial Intelligence (IJCAI 2011),2011.


Week           Date Topic Readings
Week 1 10/2

Week 2 10/9

Week 3 10/16

Week 4

Week 5 10/30

Week 6 11/6

Week 7 11/13

Week 8 11/20

Week 9

Week 10