Abstract
The paper describes the possibilities and basic means of constructing intelligent systems of real-time based on an integrated approach. A multi-agent approach, flexible decision search algorithms, forecasting algorithms based on reinforced learning are used. The architecture of forecasting module, module of deep reinforced learning and the architecture of the forecasting subsystem are given. The results of computer simulation of reinforcement learning algorithms based on temporal differences are presented and the corresponding recommendations for their use in multi-agent systems are given.
The work was supported by the Russian Foundation for Basic Research, projects №№ 18-01- 00201 a, 18-01-00459 a, 18-51-00007 Bel-a, 18-29-03088 MK.
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
References
Sutton, R.S., Barto, A.G.: Reinforcement Learning. The MIT Press, London (2012)
Vagin, V.N., Eremeev, A.P.: Some basic principles of design of intelligent systems for supporting real-time decision making. J. Comput. Syst. Sci. Int. 6, 953–961 (2001)
Bashlykov, A.A., Eremeev, A.P.: Fundamentals of Design of Intelligent Decision Support Systems in Nuclear Power Engineering: Textbook. INFRA-M, Moscow (2018). (in Russian)
Mnih, V., Badia, A.P., Mirza, M., Graves, A., Harley, T., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd International Conference on Machine Learning (PMLR 48), pp. 1928–1937 (2016)
Nikolenko, S., Kadurin, A., Archangelskaya, E.: Deep learning. In: Immersion in the World of Neural Networks. PITER, St. Petersburg (2017). (in Russian)
Eremeev, A.P., Kozhukhov, A.A., Guliakina, N.A.: Implementation of intelligent forecasting subsystem of real-time. In: Proceedings of the International Conference on Open Semantic Technologies for Intelligent Systems (OSTIS-2019), Minsk, pp. 201–204 (2019)
Alekhin, R., Varshavsky, P., Eremeev, A., Kozhevnikov, A.: Application of the case-based reasoning approach for identification of acoustic-emission control signals of complex technical objects. In: 2018 3rd Russian-Pacific Conference on Computer Technology and Applications (RPC), pp. 28–31 (2018)
Busoniu, L., Babuska, R., De Schutter, B.: Multi-agent reinforcement learning: an overview. In: Innovations in Multi-agent Systems and Applications, vol. 310, pp. 183–221. Springer, Heidelberg (2010)
Eremeev, A.P., Kozhukhov, A.A.: About implementation of machine learning tools in real-time intelligent systems. J. Softw. Syst. 2, 239–245 (2018). (in Russian)
Sort, J., Singh, S., Lewis, R.L.: Variance-based rewards for approximate Bayesian reinforcement learning. In: Proceedings of Uncertainty in Artificial Intelligence, pp. 564–571 (2010)
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., et al.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)
Li, Y.: Deep reinforcement learning: an overview, arXiv (2017). http://arxiv.org/abs/1701.07274
Hansen, E.A., Zilberstein, S.: Monitoring and control of anytime algorithms: a dynamic programming approach. J. Artif. Intell. 126, 139–157 (2001)
Mangharam, R., Saba, A.: Anytime algorithms for GPU architectures. In: IEEE Real-Time Systems Symposium (2011)
Eremeev, A.P., Gerasimova, A.T., Kozhukhov, A.A.: Comparative analysis of machine reinforcement learning methods applied to real time systems. In: Proceedings of the International Conference on Intelligent Systems and Information Technologies (IS&IT 2019), Taganrog, vol. 1, pp. 213–222 (2019)
Golenkov, V.V., Gulyakina, N.A., Grakova, N.V., Nikulenka, V.Y., Eremeev, A.P., Tarasov, V.B.: From training intelligent systems to training their development means: In: Proceedings of the International Conference on Open Semantic Technologies for Intelligent Systems (OSTIS-2018), Minsk, vol. 2, no. 8, pp. 81–99 (2018)
Eremeev, A.P., Kozhukhov, A.A., Golenkov, V.V., Guliakina, N.A.: On the implementation of the machine learning tools in intelligent systems of real-time. J. Softw. Syst. 31(2), 81–99 (2018). (in Russian)
Likhachev, M., Ferguson, D., Gordon, G., Stentz, A., Thrun, S.: Anytime dynamic A*: an anytime, replanning algorithm. In: Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), pp. 262–271 (2005)
Eremeev, A.P., Kozhukhov, A.A.: About the integration of learning and decision-making models in intelligent systems of real-time. In: Proceedings of the Second International Scientific Conference “Intelligent Information Technologies for Industry” (IITI 2018), vol. 2, pp. 181–189. Springer (2018)
Eremeev, A.P., Kozhukhov, A.A.: Methods and program tools based on prediction and reinforcement learning for the intelligent decision support systems of real-time. In: Proceedings of the Second International Scientific Conference “Intelligent Information Technologies for Industry” (IITI 2017), vol. 1, pp. 74–83. Springer (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Eremeev, A.P., Kozhukhov, A.A., Gerasimova, A.E. (2020). Implementation of the Real-Time Intelligent System Based on the Integration Approach. In: Kovalev, S., Tarassov, V., Snasel, V., Sukhanov, A. (eds) Proceedings of the Fourth International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’19). IITI 2019. Advances in Intelligent Systems and Computing, vol 1156. Springer, Cham. https://doi.org/10.1007/978-3-030-50097-9_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-50097-9_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-50096-2
Online ISBN: 978-3-030-50097-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)