Abstract
This paper considers aspects of applying machine learning methods to existing ways of modeling intelligent agent behavior. Such a goal is considered to enable agents to improve their performance in competitive models. An overview of existing machine learning methods is given. Ways of modeling the behavior of agents are considered. The most advantageous combination of machine learning and behavioral modeling approaches is identified. The advantages and disadvantages of existing methods are considered. The intelligent agent models are implemented based on behavioral trees with the introduction of reinforcement learning. A test platform with an integrated agent competition model is implemented. The ability of the developed intelligent agent behavior model to win in competition with agents equipped with different variants of traditional tree-based behaviors has been tested on the basis of the developed platform. The workability and benefits of using the developed behavioral model were analyzed in relation to the potential of the chosen combination of techniques.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Burova, A., Burov, S., Parygin, D., Gurtyakov, A., Rashevskiy, N.: Distributed administration of multi-agent model properties. In: CEUR Workshop Proceedings, vol. 3090, pp. 24–33. CEUR (2022)
Burov, S., Parygin, D., Finogeev, A., Ather, D., Rashevskiy, N.: Rule-based pedestrian simulation. In: Proceedings of the 2nd International Conference on “Advancement in Electronics & Communication Engineering”, Ghaziabad, India, 14–15 July 2022. SSRN (2022)
Anokhin, A., Burov, S., Parygin, D., Rent, V., Sadovnikova, N., Finogeev, A.: Development of Scenarios for Modeling the Behaviour of People in an Urban Environment. In: Kravets, A.G., Bolshakov, A.A., Shcherbakov, M. (eds.) Society 5.0: Cyberspace for Advanced Human-Centered Society. SSDC, vol. 333. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-63563-3_9
Davtian, A., Shabalina, O., Sadovnikova, N., Berestneva, O., Parygin, D.: Principles for Modeling Information Flows in Open Socio-Economic Systems. In: Kravets, A.G., Bolshakov, A.A., Shcherbakov, M. (eds.) Society 5.0: Human-Centered Society Challenges and Solutions. SSDC, vol. 416. Springer, Cham(2022). https://doi.org/10.1007/978-3-030-95112-2_14
Creating artificial intelligence for games – from design to optimization. https://habr.com/company/intel/blog/265679/. Accessed 29 March 2023
Applying Goal-Oriented Action Planning to Games. http://alumni.media.mit.edu/~jorkin/GOAP_draft_AIWisdom2_2003.pdf. Accessed 20 March 2023
Official Halo website. https://www.halowaypoint.com/ru-ru. Accessed 21 March 2023
BioShock. https://www.bioshockgame.com/. Accessed 17 March 2023
SPORE. https://www.ea.com/ru-ru/games/spore/spore. Accessed 15 March 2023
Behavioral trees or finite state machines. https://opsive.com/support/documentation/behavior-designer/behavior-trees-or-finite-state-machines/. Accessed 24 March 2023
Behavior trees for AI: How they work. https://www.gamasutra.com/blogs/ChrisSimpson/20140717/221339/Behavior_trees_for_AI_How_they_work.php. Accessed 4 April 2023
Building your own Basic Behaviour tree in Unity. https://hub.packtpub.com/building-your-own-basic-behavior-tree-tutorial/. Accessed 5 April 2023
Machine learning. http://www.machinelearning.ru/. Accessed 8 March 2023
Introduction to reinforcement learning for beginners. https://proglib.io/p/reinforcement-learning/. Accessed 10 March 2023
Reinforcement Learning. https://medium.com/@pavelkordik/reinforcement-learning-the-hardest-part-of-machine-learning-b667a22995ca. Accessed 25 Feb 2023
Deep Reinforcement Learning. https://towardsdatascience.com/how-to-teach-an-ai-to-play-games-deep-reinforcement-learning-28f9b920440a. Accessed 7 April 2023
Deep Learning. https://vk.com/deeplearning. Accessed 11 April 2023
OpenFace. https://cmusatyalab.github.io/openface/. Accessed 4 April 2023
Colornet. https://github.com/pavelgonchar/colornet. Accessed 28 March 2023
Magenta. https://github.com/tensorflow/magenta. Accessed 28 March 2023
The neural networks behind Google Voice transcription. https://ai.googleblog.com/2015//the-neural-networks-behind-google-voice.html. Accessed 1 April 2023
Deeper learning: Opportunities, perspectives and a bit of history. https://habr.com/company/it-grad/blog/309024/. Accessed 15 March 2023
Bringing gaming to life with AI and deep learning. https://www.oreilly.com/ideas/ bringing-gaming-to-life-with-ai-and-deep-learning. Accessed 20 March 2023
DeepMind. https://deepmind.com/. Accessed 2 March 2023
Human-level control through Deep Reinforcement Learning. https://deepmind.com/research/dqn/. Accessed 2 March 2023
An introduction to Deep Q-Learning. https://medium.freecodecamp.org/an-introduction-to-deep-q-learning-lets-play-doom-54d02d8017d8. Accessed 14 March 2023
Unity: A General Platform for Intelligent Agents. https://arxiv.org/abs/1809.02627. Accessed 11 April 2023
Sadovnikova, N., Savina, O., Parygin, D., Churakov, A., Shuklin, A.: Application of scenario forecasting methods and fuzzy multi-criteria modeling in substantiation of urban area development strategies. Information 14(4), art. no. 241. MDPI (2023)
Zelenskiy, I., Parygin, D., Savina, O., Finogeev, A., Gurtyakov, A.: Effective implementation of integrated area development based on consumer attractiveness assessment. Sustainability 14(23), art. no. 16239. MDPI (2022)
Acknowledgments
The study has been supported by the grant from the Russian Science Foundation (RSF) and the Administration of the Volgograd Oblast (Russia) No. 22-11-20024, https://rscf.ru/en/project/22-11-20024/. The authors express gratitude to colleagues from the Department of Digital Technologies for Urban Studies, Architecture and Civil Engineering, VSTU involved in the development of the project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Anokhin, A., Ereshchenko, T., Parygin, D., Khoroshun, D., Kalyagina, P. (2023). Applying Machine Learning and Agent Behavior Trees to Model Social Competition. In: Kabassi, K., Mylonas, P., Caro, J. (eds) Novel & Intelligent Digital Systems: Proceedings of the 3rd International Conference (NiDS 2023). NiDS 2023. Lecture Notes in Networks and Systems, vol 784. Springer, Cham. https://doi.org/10.1007/978-3-031-44146-2_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-44146-2_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44145-5
Online ISBN: 978-3-031-44146-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)