Learning for Planning: Resources, Papers, and Researchers  


Below we give links to web resources, papers, and researchers related to machine learning for automated planning. We would appreciate any pointers to additional material. The focus of this page is primarily on work dealing with learning domain-specific control knowledge for 'traditional' AI planning domains and planners. Only a small amount of work on 'modern' reinforcement learning has been included in this survey---see the UMass Repository for more on that topic.

Resources

  • AI Planning Resources
  • U.K. Planning and Scheduling Special Interest Group
  • Pat Langley's Learning in Planning and Problem Solving Page
  • UMass Reinforcement Learning Repository
  • 2002 International Planning Competition

  • Related Papers

    Planning with Control Knowledge
  • Bacchus, F. & Kabanza, F. (2000). Using Temporal Logics to Express Search Control Knowledge for Planning. Artificial Intelligence, volume 16, pages 123--191. (html)
  • Bacchus, F. & Yang, Q. (1994). Downward Refinement and the Efficiency of Hierarchical Problem Solving. Artificial Intelligence Journal, Vol. 71, No. 1. pages 43--100.(Postscript)
  • Barrett, A. & Weld, D. (1994). Task-Decomposition via Plan Parsing. Proceedings of AAAI-94. (html)
  • Huang, Y., Selman, B. & Kautz, H. (1999). Control Knowledge in Planning: Benefits and Tradeoffs. National Conference on Artificial Intelligence. (html)
  • Kvarnström, J. & Doherty, P. (2001). TALplanner: A Temporal Logic Based Forward Chaining Planner. Annals of Mathematics and Artificial Intelligence, 30:119-169. (html)
  • Minton, S. (1996). Is There Any Need for Domain-Dependent Control Information?: A Reply. Proceedings of the National Conference on Artificial Intelligence. (html)
  • Son, T., Baral, C. & McIlraith, S. (2001). Planning with Different Forms of Domain-Dependent Control Knowledge - An Answer Set Programming Approach. International Conference on Logic Programming and Nonmonotonic Reasoning. (html)
  • Srivastava, B. & Kambhampati, S. (1998). Synthesizing Customized Planners from Specifications. Journal of Artificial Intelligence Research, 8:93--128. (html)
  • Wilkins, D. & DesJardins, M. (2001). A Call for Knowledge-based Planning. AI Magazine, Spring 2001, volume 22, number 1, pages 99-115. (html)
  • Learning Control Knowledge for Planning
  • Ambite, J., Knoblock, C. & Minton, S. (2000). Learning Plan Rewriting Rules. Conference on Artificial Intelligence Planning Systems.(html)
  • Aler, R., Borrajo, D. & Isasi, P. (2000). Knowledge representation issues in control knowledge learning. Proceedings of the Seventeenth International Conference on Machine Learning.(html)
  • Aler, R., Borrajo, D. & Isasi, P. (2002). Using genetic programming to learn and improve control knowledge. Artificial Intelligence. (Postscript)
  • Barto, A., Bradtke, S., & Singh, S. (1995). Learning to Act Using Real-Time Dynamic Programming. Artificial Intelligence 72 (1-2), pp. 81-138. (html)
  • Borrajo, D., Camacho, D., & Silva, A. (1999). Multistrategy relational learning of heuristics for problem solving. Research and Development in Intelligent Systems XVI. Proceedings of Expert Systems 99, The 19th SGES International Conference on Knowledge Based Systems and Applied Artificial Intelligence. (html)
  • Borrajo, D. & Veloso, M. (1996). Lazy incremental learning of control knowledge for efficiently obtaining quality plans. AI Review Journal, 10:1-34. (html)
  • Cohen, W. (1990). Learning Approximate Control Rules of High Utility. International Conference on Maching Learning. (html)
  • DeJong, G. & Mooney, R. (1986). Explanation-Based Learning: An Alternative View. Machine Learning, 1(2).
  • Dietterich, T. & Flann, N. (1997). Explanation-Based Learning and Reinforcement Learning: A Unified View. Machine Learning, 28(2-3):169--210. (html)
  • Dzeroski, S., Raedt, L. & Driessens, K. (2001). Relational Reinforcement Learning. Machine Learning, 43(1--2):7--52. (Postript)
  • Estlin, T. & Mooney, R. (1996). Multi-Strategy Learning of Search Control for Partial-Order Planning. National Conference on Artificial Intelligence. (html)
  • Estlin, T. & Mooney, R. (1997). Learning to Improve Both Efficiency and Quality for Planning. International Joint Conference on Artificial Intelligence. (html)
  • Fikes, R., Hart, P. & Nilsson, N. (1972). Learning and Executing Generalized Robot Plans. Artificial Intelligence, 3:251-288.
  • Find, E. & Yang, Q. (1997). Automatically selecting and using primary effects in planning: theory and experiments. Artificial Intelligence 89 (1-2) pp. 285-315. (Postscript)
  • Finkelstein, L. & Markovitch, S. (1998). A Selective Macro-learning Algorithm and its Application to the NxN Sliding-Tile Puzzle. Journal of Artificial Intelligence Research, 8:223-263. (html)
  • Garland, A. & Lesh, N. (2002). Learning Hierarchical Task Models by Demonstration. TR-2002-04, Mitsubishi Research Laboratories. (Postscript)
  • Güvenir, H. & Ernst, G. (1990). Learning problem solving strategies using refinement and macro generation. Artificial Intelligence, 44 (1-2), pp. 209-243.
  • Huang, Y., Selman, B. & Kautz, H. (2000). Learning Declarative Control Rules for Constraint-Based Planning. Seventeenth International Conference on Machine Learning. (html)
  • Kambhampati, S., Katukam, S. & Qu, Y. (1996). Failure driven dynamic search control for partial order planners: an explanation based approach. Artificial Intelligence, 88 (1-2). pp. 253-315. (Postscript)
  • Khardon, R. (1999). Learning to take Actions. Machine Learning, 35(1):57-90. (html)
  • Khardon, R. (1999). Learning Action Strategies for Planning Domains. Artificial Intelligence, 113:125-148. (html)
  • Knoblock, C. (1994). Automatically generating abstractions for planning. Artificial Intelligence, 68(2). (html)
  • Koenig, S. (2001). Minimax real-time heuristic search. Artificial Intelligence 129 (1-2), pp. 165-197. (html)
  • Korf, R. (1985). Macro-operators: A weak method for learning. Artificial Intelligence, 26 (1), pp. 35-77
  • Korf, R. (1990). Real-Time Heuristic Search. Artificial Intelligence 42 (2-3), pp. 189-211. (Postscript)
  • Leckie, C. & Zukerman, I. (1998). Inductive learning of search control rules for planning. Artificial Intelligence 101 (1-2), pp. 63-98. (PDF)
  • Ledeniov, O. & Markovitch, S. (1998). The Divide-and-Conquer Subgoal-Ordering Algorithm for Speeding up Logic Inference. Journal of Artificial Intelligence Research, 9. (html)
  • Lorenzo, D., Otero, R. (2001). Learning Logic Programs for Action Selection in Planning. EPIA 2001. Portuguese Conference on Artificial Intelligence 3rd International Workshop on Extraction of Knowledge from Databases. (html)
  • Mahadevan, S., Mitchell, T., Mostow, J., Steinberg, L. & Tadepalli, P. (1993). An apprentice-based approach to knowledge acquisition. Artificial Intelligence 64 (1) pp. 1-52. (Postscript)
  • Martin, M. & Geffner, H. (2000). Learning generalized policies in planning using concept languages. Internatinal Conference on Knowledge Representation and Reasoning. (html)
  • Minton S. (1990). Quantitative Results Concerning the Utility of Explanation-Based Learning. Artificial Intelligence, 42.
  • Minton S., Carbonell, J., Knoblock, C., Kuokka, D.R., Etzioni, O. & Gil, Y. (1989). Explanation-Based Learning: A Problem-Solving Perspective. Artificial Intelligence, 40.
  • Mitchell, T., Keller, R. & Kedar-Cabelli, S. (1986). Explanation-Based Generalization: A Unifying View. Machine Learning, 1(1):47--80.
  • Okhtay, I., Nau, D., Munoz-Avila, H. & Aha, D. (2002). CaMeL: Learning Method Preconditions for HTN Planning. International Conference on AI Planning and Scheduling. (PDF)
  • Pérez, A. (1996). Representing and Learning Quality-Improving Search Control Knowledge. Proceedings of the Thirteenth International Conference on Machine Learning.(html)
  • Reddy, C. & Tadepalli, P. Learning Goal-Decomposition Rules using Exercises. Proceedings of International Conference on Machine Learning. (html)
  • Schmid, U. & Wysotzki, F. (2000). Applying inductive program synthesis to macro learning. Proceedings of AIPS. (Postscript)
  • Tadepalli, P. & Natarajan, B. (1996). A Formal Framework for Speedup Learning from Problems and Solutions. Journal of AI Research 4:445-475. (html)
  • Upal, M. A. & Elio, R. (1998). Learning to improve the quality of plans produced by partial-order planners. Knowledge Engineering and Acquisition for Planning Workshop, Fourth International Conference on Artificial Intelligence Planning Systems. (html)
  • Upal, A. & Elio, R. (1999). Learning rationales to improve plan quality for partial order planners. Proceedings of the Twelfth International FLAIRS Conference, pp. 371-377. (html)
  • Upal, A. & Elio, R. (2000). Learning rewrite rules versus search control rules to improve plan quality. Proceedings of the Canadian Conference on Artificial Intelligence, pp. 240-253. (html)
  • Veloso, M., Carbonell, J., Pérez, A., Borrajo, D., Fink, E. & Blythe, J. (1995). Integrating planning and learning: The prodigy architecture. Journal of Experimental and Theoretical AI, 7:81-120. (html)
  • Winner, E. & Veloso, M. (2002). Automatically acquiring planning templates from example plans. Proceedings of AIPS'02 Workshop on Exploring Real-World Planning. (PDF)
  • Yoon, S., Fern, A. & Givan, R. (2002). Inductive Policy Selection for First-Order MDPs. Conference on Uncertainty in Artificial Intelligence. (PDF)
  • Zaki, M., Lesh, N. & Ogihara, M. (2000). PlanMine: Predicting Plan Failures using Sequence Mining. Artificial Intelligence Review, 14(6):421--446. (html)
  • Learning to Control Knowledge for Theorem Provers
  • Denzinger, J., Fuchs, M., Goller, C. & Schulz, S. (1999). Learning from Previous Proof Experience: A Survey. AR-Report AR99-4, Fakultät für Informatik, Technische Universität München. (html)
  • Denzinger, J. & Schulz, S. (2000). Automatic Acquisition of Search Control Knowledge from Multiple Proof Attempts. Information and Computation, 162:59-79. (html)

  • People

  • Ricardo Aler
  • Daniel Borrajo
  • William Cohen
  • Gerald DeJong
  • Renée Elio
  • Tara Estlin
  • Andrew Garland
  • Hector Geffner
  • Russell Greiner
  • Okhtay Ilghami
  • Subbarao Kambhampati
  • Henry Kautz
  • Roni Khardon
  • Craig Knoblock
  • Richard Korf
  • Pat Langley
  • Neal Lesh
  • Shaul Markovitch
  • Steven Minton
  • Tom Mitchell
  • Raymond Mooney
  • Alicia Pérez
  • Ute Schmid
  • Stephan Schultz
  • Prasad Tadepalli
  • Manuela Veloso
  • Elly Winner
  • Qiang Yang
  • Mohammed Zaki