Abstract
Artificial Intelligence (AI) planning technology represents one of the most efficient solutions to guide goal driven agents in domain problems which are mostly characterized by problem solving features. The current proliferation of physical and virtual autonomous agents have therefore triggered a growing interest in the automatic acquisition of action models, which can take advantage of the observation capabilities of agents, which sense world states through their sensors. In this work we present a Neural Network (NN) based approach for learning AI planning action models by observation in noisy environments. The system learns by observing a set of execution patterns of the same action in different contexts. The perceptions of both pre/post action execution states are used to train the NN learning component and are assumed to be affected by noise, which could be due to inaccurate reading or malfunctioning of the sensors. Preliminary experiments shows that the proposed NN learning module seems to be more resilient to unforeseen situations with respect to traditional propositional-based approaches to action model learning.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ai-Chang, M., et al.: MAPGEN: mixed-initiative planning and scheduling for the mars exploration rover mission. IEEE Intell. Syst. 19(1), 8–12 (2004). https://doi.org/10.1109/MIS.2004.1265878
Arora, A., Fiorino, H., Pellier, D., Métivier, M., Pesty, S.: A review of learning planning action models. Knowl. Eng. Rev. 33, e20 (2018). https://doi.org/10.1017/S0269888918000188
Balac, N., Gaines, D.M., Fisher, D.: Learning action models for navigation in noisy environments (2000)
Chiancone, A., Franzoni, V., Niyogi, R., Milani, A.: Improving link ranking quality by quasi-common neighbourhood, pp. 21–26. IEEE Press (2015). https://doi.org/10.1109/ICCSA.2015.19
Cresswell, S., Gregory, P.: Generalised domain model acquisition from action traces. In: ICAPS 2011 - Proceedings of the 21st International Conference on Automated Planning and Scheduling (2011)
Fikes, R.E., Nilsson, N.J.: STRIPS: a new approach to the application of theorem proving to problem solving. Artif. Intell. 2(3–4), 189–208 (1971). https://doi.org/10.1016/0004-3702(71)90010-5
Franzoni, V., Leung, C.H.C., Li, Y., Mengoni, P., Milani, A.: Set similarity measures for images based on collective knowledge. In: Gervasi, O., et al. (eds.) ICCSA 2015. LNCS, vol. 9155, pp. 408–417. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-21404-7_30
Franzoni, V., Li, Y., Mengoni, P.: A path-based model for emotion abstraction on Facebook using sentiment analysis and taxonomy knowledge, pp. 947–952. IEEE Press (2017)
Franzoni, V., Mencacci, M., Mengoni, P., Milani, A.: Heuristics for semantic path search in Wikipedia. In: Murgante, B., et al. (eds.) ICCSA 2014. LNCS, vol. 8584, pp. 327–340. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-09153-2_25
Franzoni, V., Milani, A.: PMING distance: a collaborative semantic proximity measure, vol. 2, pp. 442–449. IEEE Press (2012). https://doi.org/10.1109/WI-IAT.2012.226
Franzoni, V., Milani, A., Pallottelli, S., Leung, C., Li, Y.: Context-based image semantic similarity, pp. 1280–1284. IEEE Press (2016). https://doi.org/10.1109/FSKD.2015.7382127
Hoffmann, J.: FF: the fast-forward planning system. AI Mag. 22, 57 (2001)
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). https://doi.org/10.1017/S026988891200001X
Leung, C.H.C., Li, Y., Milani, A., Franzoni, V.: Collective evolutionary concept distance based query expansion for effective web document retrieval. In: Murgante, B., et al. (eds.) ICCSA 2013. LNCS, vol. 7974, pp. 657–672. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-39649-6_47
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529 (2015). https://doi.org/10.1038/nature14236
Molineaux, M., Aha, D.W.: Learning unknown event models. In: Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2014, pp. 395–401. AAAI Press (2014)
Mourao, K.: Learning probabilistic planning operators from noisy observations. In: 31st Workshop of the UK Planning & Scheduling Special Interest Group (PlanSIG 2013) (2014)
Mourao, K., Zettlemoyer, L.S., Petrick, R.P.A., Steedman, M.: Learning STRIPS operators from noisy and incomplete observations, October 2012
Newton, M.A.H., Levine, J.: Implicit learning of compiled macro-actions for planning. Front. Artif. Intell. Appl. 215, 323–328 (2010)
Safaei, J., Ghassem-Sani, G.: Incremental learning of planning operators in stochastic domains. In: van Leeuwen, J., Italiano, G.F., van der Hoek, W., Meinel, C., Sack, H., Plášil, F. (eds.) SOFSEM 2007. LNCS, vol. 4362, pp. 644–655. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-69507-3_56
Shah, M., et al.: Knowledge engineering tools in planning: state-of-the-art and future challenges. Knowl. Eng. Plann. Sched. 53, 53 (2013)
Shen, W.M.: Discovery as autonomous learning from the environment. Mach. Learn. 12(1), 143–165 (1993). https://doi.org/10.1023/A:1022827618816
Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529, 484 (2016)
Wang, X.: Learning by observation and practice: an incremental approach for planning operator acquisition. In: Machine Learning Proceedings 1995, January, pp. 549–557 (1995). https://doi.org/10.1016/B978-1-55860-377-6.50074-8
Weber, B.G., Mateas, M., Jhala, A.: Learning from demonstration for goal-driven autonomy. In: Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2012, pp. 1176–1182. AAAI Press (2012)
Winograd, T.: Understanding Natural Language. Academic Press Inc., Orlando (1972)
Zhuo, H.H., Kambhampati, S.: Action-model acquisition from noisy plan traces. In: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, IJCAI 2013, pp. 2444–2450. AAAI Press (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Milani, A., Niyogi, R., Biondi, G. (2019). Neural Network Based Approach for Learning Planning Action Models. In: Misra, S., et al. Computational Science and Its Applications – ICCSA 2019. ICCSA 2019. Lecture Notes in Computer Science(), vol 11624. Springer, Cham. https://doi.org/10.1007/978-3-030-24311-1_38
Download citation
DOI: https://doi.org/10.1007/978-3-030-24311-1_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24310-4
Online ISBN: 978-3-030-24311-1
eBook Packages: Computer ScienceComputer Science (R0)