Abstract
The tedious, often hand-modeled, activity of designing and implementing simulation scenarios can benefit from modern-day data-driven methods, i.e., machine-learning (ML). We envision a toolchain that exploits information obtained during live operations, such as the observed maneuvers, techniques, and procedures of all interacting players in live operational settings, that serves as input into an ML-based scenario authoring process. We present a mechanism, called the Parameter Diversifier (PD), that takes a base scenario structure and synthesizes the comprehensive datasets needed for the supervised machine-learning of a scenario authoring model. The design of the PD explores and exploits low-level agent state search space as it relates to it high-level implications at the scenario level. This work demonstrates an explicit sampling of the scenario parameter search space to build an implicit model for use in simulation scenario generation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Erol, K., Hendler, J.N., Nau, D.S.: HTN planning: complexity and expressivity. In: 12th National Conference on Artificial Intelligence (1994)
Fernandez, A., Garcia, S., Hernandez, F., Chawla, N.V.: SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J. Artif. Intell. Res. 61, 863–905 (2018)
Folsom-Kovarik, J.T., Woods, A., Wray, R.E.: Designing an authorable scenario representation for instructor control over computationally tailored narrative in training. In: Proceedings of the 29th International FLAIRS Conference. AAAI Press, Key Largo (2016)
Graffeo, C., Benoit, T., Wray, R.E., Folsom-Kovarik, J.T.: Creating a scenario design workflow for dynamically tailored training in socio-cultural perception. In: Proceedings of the 2015 Cross-Cultural Decision Making Conference. Springer, Las Vegas (2015)
Haley, J., Hung, V., Bridgman, R., Timpko, N., Wray, R.E.: Low level entity state sequence mapping to high level behavior via a deep LSTM model. In: 20th International Conference on Artificial Intelligence, Las Vegas (2018)
Jennings-Teats, M., Smith, G., Wardrip-Fruin, N.: Polymorth: a model for dynamic level generation. In: AAAI Conference of Artificial Intelligence and Interactive Digital Entertainment (2010)
Juul, J.: Variation over time: the transformation of space in single-screen action games. In: von Borries, F., Walz, S.P., Brinkmann, U., Böttger, M. (eds.) Space Time Play. Birkhäuser, Basel (2007)
Mayer, N., et al.: What makes good synthetic training data for learning disparity and optical flow estimation? Int. J. Comput. Vis. 126(9), 942–960 (2018)
Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)
Sorenson, N., Pasquier, P.: Towards a generic framework for automated video game level creation. In: Di Chio, C., et al. (eds.) EvoApplications 2010. LNCS, vol. 6024, pp. 131–140. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-12239-2_14
Summerville, A., et al.: Procedural content generation via machine learning (PCGML). IEEE Trans. Games 10(3), 257–270 (2018)
Tomizawa, H.: Automated SGen In A Simulation. Master’s thesis, University of Central Florida (2006)
Wallace, S.: Behavior bounding: an efficient method for high-level behavior comparison. J. Artif. Intell. Res. 34, 165–208 (2009)
Wray, R.E., Bachelor, B., Jones, R.M., Newton, C.: Bracketing human performance to support automation for workload reduction: a case study. In: Schmorrow, D.D., Fidopiastis, C.M. (eds.) AC 2015. LNCS (LNAI), vol. 9183, pp. 153–163. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-20816-9_16
Wray, R.E., Priest, H., Walwanis, M.A., Kaste, K.: Requirements for future SAFs: beyond tactical realism. In: Interservice/Industry Training, Simulation, and Education Conference, Orlando (2015)
Zook, A., Lee-Urban, S., Riedl, M.O., Holden, H.K., Sottilare, R.A., Brawner, K.W.: Automated SGen: toward tailored and optimized military training in virtual environments. In: International Conference on the Foundations of Digital Games, pp. 164–171 (2012)
Acknowledgements
The authors thank Dr. Heather Priest and Mr. Samuel Parmenter for their contributions to our approach. The opinions expressed here are not necessarily those of the Department of Defense or the sponsor of this effort: Naval Air Warfare Center Training Systems Division. This work was funded under contracts N68335-17-C-0574.
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
Hung, V., Haley, J., Bridgman, R., Timpko, N., Wray, R. (2019). Synthesizing Machine-Learning Datasets from Parameterizable Agents Using Constrained Combinatorial Search. In: Thomson, R., Bisgin, H., Dancy, C., Hyder, A. (eds) Social, Cultural, and Behavioral Modeling. SBP-BRiMS 2019. Lecture Notes in Computer Science(), vol 11549. Springer, Cham. https://doi.org/10.1007/978-3-030-21741-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-21741-9_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-21740-2
Online ISBN: 978-3-030-21741-9
eBook Packages: Computer ScienceComputer Science (R0)