Learning for Planning and Problem Solving
Most learning research concerns classification. Research in learning and planning and problem solving focuses on improving the performance of an AI planning or problem solving system through experience. Our work has focussed on integrating explanation-based learning (EBL) and inductive learning (specifically ILP) to improve the efficiency (speedup learning) and solution-quality for planning and problem solving systems by solving sample problems and learning heuristics that avoid backtracking or sub-optimal solutions.

Our work has focused on two systems:

  • SCOPE: Learning control rules for partial-order planning to improve efficiency and plan quality
  • DOLPHIN: Learning clause-selection rules for dynamic optimization of logic programs
People
Bryan Silverthorn Ph.D. Alumni bsilvert [at] cs utexas edu
Publications
     [Expand to show all 19][Minimize]
CAPE: Corrective Actions from Precondition Errors using Large Language Models 2024
Shreyas Sundara Raman, Vanya Cohen, Ifrah Idrees, Eric Rosen, Raymond Mooney, Stefanie Tellex, and David Paulius, International Conference on Robotics and Automation (ICRA) (2024).
Using Planning to Improve Semantic Parsing of Instructional Texts 2023
Vanya Cohen, Raymond Mooney, Association of Computational Linguistics (ACL), Natural Language Reasoning and Structured Explanations Workshop (2023).
Planning with Large Language Models via Corrective Re-prompting 2022
Shreyas Sundara Raman, Vanya Cohen, Eric Rosen, Ifrah Idrees, David Paulius, Stefanie Tellex, Foundation Models for Decision Making Workshop at NeurIPS 2022 (2022).
Learning Behavior Characterizations for Novelty Search 2016
Elliot Meyerson, Joel Lehman and Risto Miikkulainen, To Appear In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2016), Denver, Colorado 2016. ACM.
Object-Model Transfer in the General Video Game Domain 2016
Alexander Braylan, Risto Miikkulainen, To Appear In Proceedings of the Twelfth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 2016.
Learning Polarity from Structure in SAT 2011
Bryan Silverthorn and Risto Miikkulainen, In Theory and Applications of Satisfiability Testing (SAT) 2011. (extended abstract).
Latent Class Models for Algorithm Portfolio Methods 2010
Bryan Silverthorn and Risto Miikkulainen, In Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence 2010.
Using Multi-Strategy Learning to Improve Planning Efficiency and Quality 1998
Tara A. Estlin, PhD Thesis, Department of Computer Sciences, The University of Texas at Austin.
Learning to Improve both Efficiency and Quality of Planning 1997
Tara A. Estlin and Raymond J. Mooney, In Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence (IJCAI-97), pp. 1227-1232, Nagoya, Japan 1997.
Hybrid Learning of Search Control for Partial-Order Planning 1996
Tara A. Estlin and Raymond J. Mooney, In New Directions in AI Planning, Malik Ghallab and Alfredo Milani (Eds.), pp. 129-140, Amsterdam 1996. IOS Press.
Integrating EBL and ILP to Acquire Control Rules for Planning 1996
Tara A. Estlin and Raymond J. Mooney, Proceedings of the Third International Workshop on Multi-Strategy Learning (MSL-96) (1996), pp. 271--279.
Integrating Explanation-Based and Inductive Learning Techniques to Acquire Search-Control for Planning 1996
Tara A. Estlin, Technical Report AI96-250, Department of Computer Sciences, University of Texas.
Multi-Strategy Learning of Search Control for Partial-Order Planning 1996
Tara A. Estlin and Raymond J. Mooney, In Proceedings of the Thirteenth National Conference on Artificial Intelligence (AAAI-96), pp. 843-848, Portland, OR, August 1996.
Integrating ILP and EBL 1994
Raymond J. Mooney and John M. Zelle, Sigart Bulletin (special issue on Inductive Logic Programmming), Vol. 5, 1 (1994), pp. 12-21.
Combining FOIL and EBG to Speed-Up Logic Programs 1993
John M. Zelle and Raymond J. Mooney, In Proceedings of the 13th International Joint Conference on Artificial Intelligence, pp. 1106-1111 1993. San Francisco, CA: Morgan Kaufmann.
Learning Search-Control Heuristics for Logic Programs: Applications to Speedup Learning and Language Acquisition 1993
John M. Zelle, unpublished. Ph.D. proposal, Department of Computer Sciences, University of Texas at Austin.
Speeding-up Logic Programs by Combining EBG and FOIL 1992
John M. Zelle and Raymond J. Mooney, In Proceedings of the 1992 Machine Learning Workshop on Knowledge Compilation and Speedup Learning, Aberdeen, Scotland, July 1992.
The Effect of Rule Use on the Utility of Explanation-Based Learning 1989
Raymond J. Mooney, In Proceedings of the 11th International Joint Conference on Artificial Intelligence, pp. 725-730 1989. San Francisco, CA: Morgan Kaufmann.
Generalizing the Order of Operators in Macro-Operators 1988
Raymond J. Mooney, In Proceedings of the Fifth International Conference on Machine Learning (ICML-88), pp. 270-283, Ann Arbor, MI, June 1988.
Projects
Borg: A General-Purpose Algorithm Portfolio System 2009 - 2013
Software/Data
Borg

The borg project includes a practical algorithm...

2011
Demos
Model-Based Visualization of Solver Performance DataBryan Silverthorn2011
Labs
Machine Learning