Find out how ICT can support biomedical and clinical researchFind out more. From Clever cars to clever farms... Embedded Systems
Latest Tweets
Dynamic Planning, Optimisation and Learning

The DPOL Project  is conducting fundamental and applied research into operations/project level planning, with an emphasis on integrating methods from machine learning and optimisation. This four way collaboration between DSTO, University of South Australia, and University of Adelaide has been particularly successful at dealing with uncertainty in planning. The project ended in July 2008.

 

Operations planning involves larges groups of people choosing and co-ordinating tasks to produce a smoothly orchestrated operation. Automatically developing robust plans with hundreds of tasks is hard. Planning becomes even harder when trying to take the uncertainty of the world into account. NICTA, the Defence Science Technology Organisation (DSTO), the University of Adelaide, and the University of South Australia are developing theoretical frameworks, algorithms and tools that formalise, abstract, and solve such planning problems.

Doug Aberdeen using DSTO's COAST toolResearch in the project has explored a wide cross section of methods previously used in planning, including Markov decision processes, SAT based planning, planning graphs and search, Petri-net unfolding, predicate logic, temporal logic, and optimisation methods.

Concrete project goals include replacing commonly used tools, such as Microsoft Project, with software that automatically plans and schedules a set of tasks. Contributions so far have developed four planning servers to support military planning tools developed by DSTO.

Methods emerging from the project have application to the broader planning community, operations researchers, control theorists, and the day-to-day project managers who would like to know how a 50% chance of rain could affect their project budget. DPOLP work is also becoming concerned with the presentation of planning information, including theoretical work in how to measure the similarity of plans, and how to present qualitatively different plans to the user from a spectrum of valid plans. Beyond traditional operations and project planning, DPOLP tools for the analysis of uncertainty contribute to the decision support and business planning domains.


Key Achievements

  •  Produced leading probabilistic temporal planners (1st and 3rd in the International Probabilistic Planning competition in 2006).
  •  Delivered three planning servers to DSTO and planning tools demonstrated in military training exercises.
People

The following people participate in the project:

Former members: Douglas Aberdeen (project leader), Olivier Buffet, S V N Viswanathan

 

Publications

Most of the publications are available at Publication Database

  1. Douglas Aberdeen.Policy-gradient methods for planning.In Advances in Neural Information Processing Systems 18 [Neural  Information Processing Systems, NIPS 2005, December 5-8, 2005, Vancouver,  British Columbia, Canada], volume 18. The MIT Press, 2005.
  2. Douglas Aberdeen and Olivier Buffet.Concurrent probabilistic temporal planning with policy-gradients.In Mark Boddy, Maria Fox, and Sylvie Thiebaux, editors,ICAPS 2007. Proceedings of the Seventeenth International Conference on  Automated Planning and Scheduling, pages 10-17. AAAI Press, 2007.
  3. Douglas Aberdeen, Olivier Buffet, and Owen Thomas.Policy-gradients for PSRs and POMDPs.In Proc. 11th Intl. Conf. Artificial Intelligence and Statistics  (AIstats). Society for Artificial Intelligence and Statistics, 2007.
  4. Douglas Aberdeen, Sylvie Thiebaux, and Lin Zhang.Decision-theoretic military operations planning.In Shlomo Zilberstein, Jana Koehler, and Sven Koenig, editors,ICAPS 2004. Proceedings of the Fourteenth International Conference on  Automated Planning and Scheduling, pages 402-412, 2004.
  5. Blai Bonet, Patrik Haslum, Sarah Hickmott, and Sylvie Thiebaux.Directed unfolding of Petri nets.In LNCS Transactions on Petri Nets and Other Models of  Concurrency, volume 5100 of Lecture Notes in Computer Science, pages  172-198. Springer-Verlag, 2008.
  6. Olivier Buffet.Reachability analysis for uncertains SSPs.In Tools with Artificial Intelligence, 2005. ICTAI 05. 17th  International Conference on, pages 515-522. IEEE, 2005.
  7. Olivier Buffet.Reachability analysis for uncertain SSPs.International Journal on Artificial Intelligence Tools,  16(4):725-749, 2007.
  8. Olivier Buffet and Douglas Aberdeen.Planification robuste avec (L)RTDP.In Francois Denis, editor, Actes de CAP 05, Conference  francophone sur l'apprentissage automatique - 2005, Nice, France, du 31 mai  au 3 juin 2005, pages 127-142. PUG, 2005.
  9. Olivier Buffet and Douglas Aberdeen.Robust planning with (L)RTDP.In Leslie Pack Kaelbling, editor, Proceedings of the 19th  International Joint Conference on Artificial Intelligence, pages 1214-1219.  Professional Book Center, 2005.
  10. Olivier Buffet and Douglas Aberdeen.Policy-gradient for robust planning.In Actes de la conférence francophone sur l'apprentissage  automatique (CAp'06), 2006.
  11. Olivier Buffet and Douglas Aberdeen.FF+FPG: Guiding a policy-gradient planner.In Mark Boddy, Maria Fox, and Sylvie Thiebaux, editors,ICAPS 2007. Proceedings of the Seventeenth International Conference on  Automated Planning and Scheduling, pages 42-48. AAAI Press, 2007.
  12. Olivier Buffet and Douglas Aberdeen.The factored policy gradient planner (FPG).Artificial Intelligence, 2009.to appear.
  13. Esra Erdem and Alfredo Gabaldon.Cumulative effects of concurrent actions on numeric-valued fluents.In Proceedings of the 20th National Conference on Artificial  Intelligence (AAAI-2005), pages 627-632. AAAI Press, 2005.
  14. Esra Erdem and Alfredo Gabaldon.Representing action domains with numeric-valued fluents.In Michael Fisher, Wiebe van der Hoek, Boris Konev, and Alexei  Lisitsa, editors, Logics in Artificial Intelligence, 10th European  Conference, JELIA 2006, Liverpool, UK, September 13-15, 2006, Proceedings,  number 4160 in Lecture Notes in Computer Science, pages 151-163.  Springer-Verlag, 2006.
  15. Alfredo Gabaldon.Formalizing complex task libraries in Golog.In Gerhard Brewka, Silvia Coradeschi, Anna Perini, and Paolo  Traverso, editors, ECAI 2006. Proceedings of the 17th European  Conference on Artificial Intelligence, pages 755-756. IOS Press, 2006.
  16. Alfredo Gabaldon and Gerhard Lakemeyer.ESP: A logic of only-knowing, noisy sensing and acting.In Proceedings of the 22nd AAAI Conference on Artificial  Intelligence (AAAI-07), pages 974-979. AAAI Press, 2007.
  17. Robby Goetschalckx, Scott Sanner, and Kurt Driessens.Reinforcement learning with the use of costly features.In Malik Ghallab, Constantine D. Spyropoulos, and Nikos Fakotakis,  editors, ECAI 2008. Proceedings of the 18th European Conference on  Artificial Intelligence, pages 779-780. IOS Press, 2008.
  18. Charles Gretton and Sylvie Thiébaux.Exploiting first-order regression in inductive policy selection.In David Maxwell Chickering and Joseph Y. Halpern, editors, UAI  '04, Proceedings of the 20th Conference in Uncertainty in Artificial  Intelligence, July 7-11 2004, Banff, Canada, pages 217-225. AUAI Press,  2004.
  19. Patrik Haslum.Reducing accidental complexity in planning problems.In Manuela Veloso, editor, Proceedings of the 20th International  Joint Conference on Artificial Intelligence, pages 1898-1903. AAAI Press,  2007.
  20. Patrik Haslum.A new approach to tractable planning.In Jussi Rintanen, Bernhard Nebel, J. Christopher Beck, and Eric  Hansen, editors, ICAPS 2008. Proceedings of the Eighteenth International  Conference on Automated Planning and Scheduling, pages 132-139. AAAI Press,  2008.
  21. Patrik Haslum, Malte Helmert, Blai Bonet, Adi Botea, and Sven Koenig.Domain-independent construction of pattern database heuristics for  cost-optimal planning.In Proceedings of the 22nd AAAI Conference on Artificial  Intelligence (AAAI-07), pages 1007-1012. AAAI Press, 2007.
  22. Malte Helmert, Patrik Haslum, and Joerg Hoffmann.Flexible abstraction heuristics for optimal sequential planning.In Mark Boddy, Maria Fox, and Sylvie Thiebaux, editors,ICAPS 2007. Proceedings of the Seventeenth International Conference on  Automated Planning and Scheduling, pages 176-183. AAAI Press, 2007.
  23. Malte Helmert, Patrik Haslum, and Joerg Hoffmann.Explicit-state abstraction: A new method for generating heuristic  functions.In Proceedings of the 23rd AAAI Conference on Artificial  Intelligence (AAAI-08), pages 1547-1550, 2008.
  24. Sarah Hickmott, Jussi Rintanen, Sylvie Thiebaux, and Lang White.Planning via Petri net unfolding.In Manuela Veloso, editor, Proceedings of the 20th International  Joint Conference on Artificial Intelligence, pages 1904-1911. AAAI Press,  2007.
  25. Iain Little, Douglas Aberdeen, and S. Thiebaux.Prottle: A probabilistic temporal planner.In Proceedings of the 20th National Conference on Artificial  Intelligence (AAAI-2005), pages 1181-1186. AAAI Press, 2005.
  26. Iain Little and Sylvie Thiebaux.Concurrent probabilistic planning in the Graphplan framework.In Derek Long, Stephen F. Smith, Daniel Borrajo, and Lee McCluskey,  editors, ICAPS 2006. Proceedings of the Sixteenth International  Conference on Automated Planning and Scheduling, pages 263-273. AAAI Press,  2006.
  27. Silvia Richter, Douglas Aberdeen, and Jin Yu.Natural actor-critic for road traffic optimisation.In Advances in Neural Information Processing Systems 19,  Proceedings of the Twentieth Annual Conference on Neural Information  Processing Systems, Vancouver, British Columbia, Canada, December 4-7, 2006,  pages 1169-1176. The MIT Press, 2006.
  28. Jussi Rintanen.Compact representation of sets of binary constraints.In Gerhard Brewka, Silvia Coradeschi, Anna Perini, and Paolo  Traverso, editors, ECAI 2006. Proceedings of the 17th European  Conference on Artificial Intelligence, pages 143-147. IOS Press, August  2006.
  29. Jussi Rintanen.Unified definition of heuristics for classical planning.In Gerhard Brewka, Silvia Coradeschi, Anna Perini, and Paolo  Traverso, editors, ECAI 2006. Proceedings of the 17th European  Conference on Artificial Intelligence, pages 600-604. IOS Press, August  2006.
  30. Jussi Rintanen.Asymptotically optimal encodings of conformant planning in QBF.In Proceedings of the 22nd AAAI Conference on Artificial  Intelligence (AAAI-07), pages 1045-1050. AAAI Press, 2007.
  31. Jussi Rintanen.Complexity of concurrent temporal planning.In Mark Boddy, Maria Fox, and Sylvie Thiebaux, editors,ICAPS 2007. Proceedings of the Seventeenth International Conference on  Automated Planning and Scheduling, pages 280-287. AAAI Press, 2007.
  32. Jussi Rintanen.Planning graphs and propositional clause-learning.In Gerhard Brewka and Patrick Doherty, editors, Principles of  Knowledge Representation and Reasoning: Proceedings of the Eleventh  International Conference (KR 2008), pages 535-543. AAAI Press, 2008.
  33. Jussi Rintanen.Regression for classical and nondeterministic planning.In Malik Ghallab, Constantine D. Spyropoulos, and Nikos Fakotakis,  editors, ECAI 2008. Proceedings of the 18th European Conference on  Artificial Intelligence, pages 568-571. IOS Press, 2008.
  34. Nicol Schraudolph, Jin Yu, and Douglas Aberdeen.Fast online policy-gradient learning with SMD gain vector  adaptation.In Advances in Neural Information Processing Systems 18 [Neural  Information Processing Systems, NIPS 2005, December 5-8, 2005, Vancouver,  British Columbia, Canada], volume 18. The MIT Press, 2006.
  35. Sylvie Thiébaux, Charles Gretton, John K. Slaney, David Price, and Froduald  Kabanza.Decision-theoretic planning with non-Markovian rewards.Journal of Artificial Intelligence Research, 25:17-74, 2006.
  36. Xinhua Zhang, Douglas Aberdeen, and S. V. N. Vishwanathan.Conditional random fields for multi-agent reinforcement learning.In Zoubin Ghahramani, editor, Machine Learning, Proceedings of  the Twenty-Fourth International Conference (ICML 2007), Corvalis, Oregon,  USA, June 20-24, 2007, pages 1143-1150. ACM, 2007.