Abstract
The paper considers integrated tools based on multi-agent temporal differences reinforcement learning and statistical modules. Implemented algorithms of reinforcement learning methods are described. The possibilities of including anytime algorithms into the forecasting subsystem type of intelligent decision support system of real-time for improving performance and reducing response and execution time were proposed. The work is supported by RFBR and BRFBR.
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
Sutton, R.S., Barto, A.G.: Reinforcement Learning. The MIT Press, London (2012)
Vagin, V.N., Eremeev, A.P.: Some basic construction principles of real-time intelligent decision support systems. J. Theor. manag. Syst. 6, 114–123 (2001). (in Russian). Izv. RAN
Shani, G., Brafman, R.I., Shimony, S.E.: Model-based online learning of POMDPs. In: European Conference on Machine Learning, pp. 353–364 (2005)
Rybina, G.V., Parondjanov, S.S.: The Technology of Building Dynamic Intelligent Systems. MEPHI, Moscow (2011). (in Russian)
Osipov, G.S.: Methods of Artificial Intelligence, 2nd edn. FIZMATLIT, Moscow (2015). (in Russian)
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, Berlin (2010)
Eremeev, A.P., Kozhukhov, A.A.: Analysis and development of reinforcement learning methods based on temporal differences for real time intelligent systems. In: 15th National Conference on Artificial Intelligence with International Participation KII-2016, vol. 1, pp. 323–330. Universum, Smolensk (2016). (in Russian)
Eremeev, A.P., Podogov, I.U.: Generalized method of hierarchical reinforcement learning for intelligent decision support systems. J. Softw. Syst. 2, 35–39 (2008). (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)
Doshi-Velez, F., Pineau, J., Roy, N.: Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs. J. Artif. Intell. 187–188, 115–132 (2012)
Ross, S., Chaib-draa, B., Pineau, J.: Bayes-adaptive POMDPs. J. Adv. Neural Inf. Process. Syst. 20, 1225–1232 (2008)
Hansen, E.A., Zilberstein, S.: Monitoring and control of anytime algorithms: a dynamic programming approach. J. Artif. Intell. 126, 139–157 (2001)
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.: Implementation of reinforcement learning methods based on temporal differences and a multi-agent approach for real-time intelligent systems. J. Softw. Syst. 1, 28–33 (2017). (in Russian)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Eremeev, A.P., Kozhukhov, A.A. (2018). Methods and Program Tools Based on Prediction and Reinforcement Learning for the Intelligent Decision Support Systems of Real-Time. In: Abraham, A., Kovalev, S., Tarassov, V., Snasel, V., Vasileva, M., Sukhanov, A. (eds) Proceedings of the Second International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’17). IITI 2017. Advances in Intelligent Systems and Computing, vol 679. Springer, Cham. https://doi.org/10.1007/978-3-319-68321-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-68321-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68320-1
Online ISBN: 978-3-319-68321-8
eBook Packages: EngineeringEngineering (R0)