Proceedings

Transferring Learned Control-Knowledge between Planners

Download BibTeX Cite

Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 1885-1889.

© 2007 International Joint Conferences on Artificial Intelligence

Abstract

As any other problem solving task that employs search, AI Planning needs heuristics to efficiently guide the problem-space exploration. Machine learning (ML) provides several techniques for automatically acquiring those heuristics. Usually, a planner solves a problem, and a ML technique generates knowledge from the search episode in terms of complete plans (macro-operators or cases), or heuristics (also named control knowledge in planning). In this paper, we present a novel way of generating planning heuristics: we learn heuristics in one planner and transfer them to another planner. This approach is based on the fact that different planners employ different search bias. We want to extract knowledge from the search performed by one planner and use the learned knowledge on another planner that uses a different search bias. The goal is to improve the efficiency of the second planner by capturing regularities of the domain that it would not capture by itself due to its bias. We employ a deductive learning method (ebl) that is able to automatically acquire control knowledge by generating bounded explanations of the problem-solving episodes in a Graphplan-based planner. Then, we transform the learned knowledge so that it can be used by a bidirectional planner.

  1. s0: Level:(5) SUCCESS Goals=((at person1 city0) (at person0 city1)) Assignments=NIL s1: Level:(4) SUCCESS Goals=((at person1 city0) (at plane1 city1) (in person0 plane1))
  2. Assignments=(((debark person0 plane1 city1) (at person0 city1))) s2: Level:(3) SUCCESS Goals=((at person1 city0) (in person0 plane1) (fuel-level plane1 fl1) (at plane1 city0)) Assignments=(((fly plane1 city0 city1 fl1 fl0) (at plane1 city1)) ((debark person0 plane1 city1) (at person0 city1))) s3: Level:(2) SUCCESS Goals=((in person1 plane1) (fuel-level plane1 fl1) (at plane1 city0) (at person0 city0))
  3. Assignments=(((board person0 plane1 city0) (in person0 plane1)) ((debark person1 plane1 city0) (at person1 city0)) ((fly plane1 city0 city1 fl1 fl0) (at plane1 city1)) ((debark person0 plane1 city1) (at person0 city1))) s4: Level:(1) SUCCESS Goals=((in person1 plane1) (at person0 city0) (fuel-level plane1 fl2) (at plane1 city1)) Assignments=(((fly plane1 city1 city0 fl2 fl1) (fuel-level plane1 fl1)) ((board person0 plane1 city0) (in person0 plane1)) ((debark person1 plane1 city0) (at person1 city0)) ((fly plane1 city0 city1 fl1 fl0) (at plane1 city1)) ((debark person0 plane1 city1) (at person0 city1))) s5: Level:(0) SUCCESS Goals=((at person1 city1) (at person0 city0) (fuel-level plane1 fl3) (at plane1 city1))
  4. Assignments=(((board person1 plane1 city1) (in person1 plane1)) ((fly plane1 city1 city0 fl2 fl1) (fuel-level plane1 fl1)) ((board person0 plane1 city0) (in person0 plane1)) ((debark person1 plane1 city0) (at person1 city0)) ((fly plane1 city0 city1 fl1 fl0) (at plane1 city1)) ((debark person0 plane1 city1) (at person0 city1))) References
  5. B. Bonet and H. Geffner. Learning depth-first search: A unified approach to heuristic search in deterministic and non-deterministic settings, and its application to MDPs. In Proceedings of ICAPS'06, 2006.
  6. D. Borrajo and M. Veloso. Lazy incremental learning of control knowledge for efficiently obtaining quality plans. AI Review Journal. Special Issue on Lazy Learn- ing, 1997.
  7. T. Bylander. Complexity results for planning. In Pro- ceedings of the 12th International Joint Conference on Artificial Intelligence, 1991. IJCAI
  8. G. DeJong and R. Mooney. Explanation-based learning: An alternative view. Machine Learning, 1986.
  9. F. Fernández and M. Veloso. Probabilistic policy reuse in a reinforcement learning agent. In Proceedings of the AAMAS'06, 2006.
  10. T. Mitchell, R. M. Keller, and S. T. Kedar-Cabelli. Explanation-based generalization: A unifying view. Machine Learning, 1986.
  11. D. Smith and D. Weld. Temporal planning with mutual exclusion reasoning. In Proceedings of the IJCAI'99, pages 326-337, 1999. IJCAI
  12. M. E. Taylor and P. Stone. Behavior transfer for value- function-based reinforcement learning. In The Fourth International Joint Conference on Autonomous Agents and Multiagent Systems, 2005.
  13. M. Veloso, J. Carbonell, A. Pérez, D. Borrajo, E. Fink, and J. Blythe. Integrating planning and learning: The PRODIGY architecture. Journal of Experimental and Theoretical AI, 1995.
  14. T. Zimmerman and S. Kambhampati. Learning-assisted automated planning: Looking back, taking stock, going forward. AI Magazine, 2003.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards