Abstract
Automated planning deals with the problem of finding a sequence of actions leading from a given state to a desired state. The state-of-the-art automated planning techniques exploit informed forward search guided by a heuristic which is used to estimate a distance from a state to a goal state.
In this paper, we present a technique to automatically construct an efficient heuristic for a given domain. The proposed approach is based on training a deep neural network using a set of solved planning problems as training data. We use a novel way of extracting features for states developed specifically for planning applications. Our experiments show that the technique is competitive with state-of-the-art domain-independent heuristic. We also introduce a theoretical framework to formally analyze behaviour of learned heuristics. We state and prove several theorems that establish bounds on the worst-case performance of learned heuristics.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
api.planning.domains/json/classical/problems/17.
- 2.
api.planning.domains/json/classical/problems/112.
References
Arfaee, S.J., Zilles, S., Holte, R.C.: Bootstrap learning of heuristic functions. In: Felner, A., Sturtevant, N.R. (eds.) Proceedings of the Third Annual Symposium on Combinatorial Search, SOCS 2010. AAAI Press (2010)
Arfaee, S.J., Zilles, S., Holte, R.C.: Learning heuristic functions for largestate spaces. Artif. Intell. 175(16), 2075–2098 (2011)
Bisson, F., Larochelle, H., Kabanza, F.: Using a recursive neural network to learn an agent’s decision model for plan recognition. In: Twenty-Fourth International Joint Conference on Artificial Intelligence (2015)
Brunetto, R., Trunda, O.: Deep heuristic-learning in the Rubik’s cube domain: an experimental evaluation. In: Hlaváčová, J. (ed.) Proceedings of the 17th Conference ITAT 2017, pp. 57–64. CreateSpace Independent Publishing Platform (2017)
Cenamor, I., De La Rosa, T., Fernández, F.: Learning predictive models to configure planning portfolios. In: Proceedings of the 4th Workshop on Planning and Learning (ICAPS-PAL 2013) (2013)
Chen, H.C., Wei, J.D.: Using neural networks for evaluation in heuristic search algorithm. In: AAAI (2011)
Ferber, P., Helmert, M., Hoffmann, J.: Neural network heuristics for classical planning: a study of hyperparameter space. In: ECAI (2020)
Fink, M.: Online learning of search heuristics. In: Artificial Intelligence and Statistics, pp. 115–122 (2007)
Geissmann, C.: Learning heuristic functions in classical planning. Master’s thesis, University of Basel, Switzerland (2015)
Goldberg, Y.: Neural network methods for natural language processing. Synth. Lect. Hum. Lang. Technol. 10(1), 1–309 (2017)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Groshev, E., Goldstein, M., et al.: Learning generalized reactive policies using deep neural networks. In: Symposium on Integrating Representation, Reasoning, Learning, and Execution for Goal Directed Autonomy (2017)
Groshev, E., Tamar, A., Goldstein, M., Srivastava, S., Abbeel, P.: Learning generalized reactive policies using deep neural networks. In: 2018 AAAI Spring Symposium Series (2018)
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer Series in Statistics. Springer New York Inc., New York (2001). https://doi.org/10.1007/978-0-387-21606-5
Helmert, M.: Understanding Planning Tasks: Domain Complexity and Heuristic Decomposition. LNCS (LNAI), vol. 4929. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-77723-6
Helmert, M.: Concise finite-domain representations for PDDL planning tasks. Artif. Intell. 173(5), 503–535 (2009). https://doi.org/10.1016/j.artint.2008.10.013. http://www.sciencedirect.com/science/article/pii/S0004370208001926. Advances in Automated Plan Generation
Hoffmann, J., Nebel, B.: The FF planning system: fast plan generation through heuristic search. J. Artif. Intell. Res. 14, 253–302 (2001)
Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Netw. 4(2), 251–257 (1991). https://doi.org/10.1016/0893-6080(91)90009-T. http://www.sciencedirect.com/science/article/pii/089360809190009T
Jiménez, S., De la Rosa, T., Fernández, S., Fernández, F., Borrajo, D.: A review of machine learning for automated planning. Knowl. Eng. Rev. 27(4), 433–467 (2012)
Konidaris, G., Kaelbling, L.P., Lozano-Perez, T.: From skills to symbols: learning symbolic representations for abstract high-level planning. J. Artif. Intell. Res. 61, 215–289 (2018)
Martín, M., Geffner, H.: Learning generalized policies from planning examples using concept languages. Appl. Intell. 20(1), 9–19 (2004)
Nau, D., Ghallab, M., Traverso, P.: Automated Planning: Theory & Practice. Morgan Kaufmann Publishers Inc., San Francisco (2004)
Pearl, J.: Heuristics: Intelligent Search Strategies for Computer Problem Solving. The Addison-Wesley Series in Artificial Intelligence. Addison-Wesley (1984). https://books.google.cz/books?id=0XtQAAAAMAAJ
Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach, 3rd edn. Prentice Hall, Upper Saddle River (2010)
Samadi, M., Felner, A., Schaeffer, J.: Learning from multiple heuristics. In: Fox, D., Gomes, C.P. (eds.) AAAI, pp. 357–362. AAAI Press (2008)
Takahashi, T., Sun, H., Tian, D., Wang, Y.: Learning heuristic functions for mobile robot path planning using deep neural networks. In: Proceedings of the International Conference on Automated Planning and Scheduling. vol. 29, pp. 764–772 (2019)
Thayer, J., Dionne, A., Ruml, W.: Learning inadmissible heuristics during search. In: Proceedings of International Conference on Automated Planning and Scheduling (2011)
Toyer, S., Trevizan, F., Thiébaux, S., Xie, L.: Action schema networks: generalised policies with deep learning. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Trunda, O., Barták, R.: Deep learning of heuristics for domain-independent planning. In: Rocha, A.P., Steels, L., van den Herik, H.J. (eds.) Proceedings of the 12th International Conference on Agents and Artificial Intelligence, ICAART 2020, vol. 2, pp. 79–88. SCITEPRESS (2020)
Virseda, J., Borrajo, D., Alcázar, V.: Learning heuristic functions for cost-based planning. Planning and Learning, p. 6 (2013)
Yoon, S., Fern, A., Givan, R.: Learning control knowledge for forward search planning. J. Mach. Learn. Res. 9(Apr), 683–718 (2008)
Acknowledgments
Research is supported by the Czech Science Foundation project P103-18-07252S.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Trunda, O., Barták, R. (2021). Heuristic Learning in Domain-Independent Planning: Theoretical Analysis and Experimental Evaluation. In: Rocha, A.P., Steels, L., van den Herik, J. (eds) Agents and Artificial Intelligence. ICAART 2020. Lecture Notes in Computer Science(), vol 12613. Springer, Cham. https://doi.org/10.1007/978-3-030-71158-0_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-71158-0_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-71157-3
Online ISBN: 978-3-030-71158-0
eBook Packages: Computer ScienceComputer Science (R0)