Abstract
The use of agent-based models (ABMs) has become more widespread over the last two decades allowing resear chers to explore complex systems composed of heterogeneous and locally interacting entities. However, there are several challenges that the agent-based modeling community face. These relate to developing accurate measurements, minimizing a large complex parameter space and developing parsimonious yet accurate models. Machine Learning (ML), specifically deep reinforcement learning has the potential to generate new ways to explore complex models, which can enhance traditional computational paradigms such as agent-based modeling. Recently, ML algorithms have proved an important contribution to the determination of semi-optimal agent behavior strategies in complex environments. What is less clear is how these advances can be used to enhance existing ABMs. This paper presents Learning-based Actor-Interpreter State Representation (LAISR), a research effort that is designed to bridge ML agents with more traditional ABMs in order to generate semi-optimal multi-agent learning strategies. The resultant model, explored within a tactical game scenario, lies at the intersection of human and automated model design. The model can be decomposed into a format that automates aspects of the agent creation process, producing a resultant agent that creates its own optimal strategy and is interpretable to the designer. Our paper, therefore, acts as a bridge between traditional agent-based modeling and machine learning practices, designed purposefully to enhance the inclusion of ML-based agents in the agent-based modeling community.
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 subscriptionsReferences
Ardema, M., Rajan, N.: An approach to three-dimensional aircraft pursuit-evasion. Comput. Math. Appl. 13(1–3), 97–110 (1987)
Castelvecchi, D.: Can we open the black box of AI? Nature News 538(7623), 20 (2016)
Dawid, H., Gemkow, S., Harting, P., van der Hoog, S., Neugart, M.: The Eurace@Unibi Model: An Agent-Based Macroeconomic Model for Economic Policy Analysis, 1 October 2012. Bielefeld Working Papers in Economics and Management No. 05-2012 (2012)
Epstein, J.: Generative Social Science: Studies in Agent-Based Computational Modeling. Princeton University Press, Princeton (2006)
François-Lavet, V., Henderson, P., Islam, R., Bellemare, M., Pineau, J.: An Introduction to deep reinforcement learning, foundations and trends in machine learning 11(3–4) (2018)
Juliani, A., et al.: Unity: a general platform for intelligent agents. arXiv preprint arXiv:1809.02627 (2018)
Lee, K., Rucker, M., Scherer, W., Beling, P., Gerber, M., Kang. H.: Agent-based model construction using inverse reinforcement learning. In: Proceedings of the 2017 Winter Simulation Conference (WSC 2017). IEEE Press, pp. 1–12 (2017). Article 95
Li, X., Engelbrecht, A., Epitropakis, M.G.: Benchmark functions for CEC 2013 special session and competition on niching methods for multimodal function optimization. RMIT University, Evolutionary Computation, and Machine Learning Group, Australia, Technical Report, pp. 1–10 (2013)
Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning (ICML 2016), vol. 48, pp. 1928–1937. JMLR.org. (2016)
Neto, G., Lima, P.: Minimax value iteration applied to robotic soccer. In: IEEE ICRA 2005 Workshop on Cooperative Robotics, pp. 1–4 (2005)
Resnick, M.: Turtles, Termites, and Traffic Jams: Explorations in Massively Parallel Microworlds (Complex Adaptive Systems). The MIT Press, Cambridge (1997)
Ros, R., Lluis Arcos, J., Lopez, R., Veloso, M.: A case-based approach for coordinated action selection in robot soccer. Artif. Intell. 173(9–10), 1014–1039 (2009)
Rudd, D.M.: The Effects of Heuristic Problem-Solving Strategies on Seventh Grade Students’ Self-Efficacy and Level of Achievement in Mathematics. The College at Brockport (2010)
Sherwood, T., Calder, B.: Automated design of finite state machine predictors for customized processors. In: Proceedings of the 28th Annual International Symposium on Computer Architecture (ISCA 2001). Association for Computing Machinery, New York, pp. 86–97 (2001)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Tampuu, A., et al.: Multi-agent cooperation and competition with deep reinforcement learning. PloS One 12(4), e0172395 (2017)
Tang, L.G., An, B., Cheng, D.J.: An Agent Reinforcement Learning Model Based on Neural Networks. In: Li, K., Fei, M., Irwin, G.W., Ma, S. (eds.) LSMS 2007. LNCS, vol. 4688, pp. 117–127. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74769-7_14
Van der Hoog, S.: Deep Learning in Discrete-Heuristic Models: A Prospectus (2016)
Wolpert, D.H., Wheeler, K.R., et al.: General Principles of Learning-Based Multi-Agent Systems. In: Autonomous Agents, Seattle, WA. ACM (1999)
Wong, K.-C.: Evolutionary multimodal optimization: a short survey. arXiv preprint arXiv:1508.00457 (2015)
Yining, W., Yuxian, J.: An intelligent differential game on air combat decision. Flight Dyn. 21, 66–70 (2003)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Cummings, P., Crooks, A. (2020). Development of a Hybrid Machine Learning Agent Based Model for Optimization and Interpretability. In: Thomson, R., Bisgin, H., Dancy, C., Hyder, A., Hussain, M. (eds) Social, Cultural, and Behavioral Modeling. SBP-BRiMS 2020. Lecture Notes in Computer Science(), vol 12268. Springer, Cham. https://doi.org/10.1007/978-3-030-61255-9_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-61255-9_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61254-2
Online ISBN: 978-3-030-61255-9
eBook Packages: Computer ScienceComputer Science (R0)