Modeling agents strategies in players with local interaction
Keywords:
multiagent system, stochastic game, adaptive gaming method, Q-method.
Abstract
In this paper, the current topic of optimal strategies in games with local interaction is considered, the incentive training of multiagent systems in game formulation is considered. The purpose of this work is to consider the method of constructing a system with local interaction of agents based on the task of "synchronization" using the Markov model of the stochastic game. The research method is a computer program for modeling a task using the Q-method of training.
References
Watkins, C.J.C.H. Q-Learning / C.J.C.H. Watkins, P. Dayan // Machine Learning. – Kluwer Academic Publishers, Boston. – 1992. – No. 8. – PP. 279–292.
Fudenberg, D. The Theory of Learning in Games / D. Fudenberg, D.K. Levine. – Cambridge, MA: MIT Press, 1998. – 292 pp.
Hu, J. Nash Q-learning for general-sum stochastic games / J. Hu, M. P. Wellman // Machine Learning Research. – 2003. – No. 4. – PP. 1039 – 1069.
Wooldridge M. An Introduction to Multiagent Systems / M. Wooldridge. – John Wiley & Sons, 2002. – 366 pp.
Weiss, G. Multiagent Systems. A Modern Approach to Distributed Artificial Intelligence / G. Weiss, editor. – Springer Verlag, Berlin, 1996. – 643 pp.
Назин А.В. Адаптивный выбор вариантов: Рекуррентные алгоритмы / А.В. Назин, А.С. Позняк. – М.: Наука, 1986. – 288 с.
Kaelbling, Leslie. Reinforcement learning: A survey / Leslie Kaelbling, Michael L. Littman, Andrew W. Moore. Journal of Artificial Intelligence Research. – 1996. – No. 4. – PP. 237–285.
Sutton, R. S. Reinforcement Learning: An Introduction / Richard S. Sutton, Andrew G. Barto. – MIT Press, 1998. – 322 pp.
Musiyenko М., Zhuravska І., Kulakovska І., Kulakovska А. Simulation the behavior of robot sub swarm in spatial corridors. 2016 IEEE 36th ELNANO. April 19-21, 2016. Kyiv, Ukraine. Page(s) 382-387. DOI:
10.1109/ELNANO.2016.7493090 http://ieeexplore.ieee.org/document/7493090/
Fudenberg, D. The Theory of Learning in Games / D. Fudenberg, D.K. Levine. – Cambridge, MA: MIT Press, 1998. – 292 pp.
Hu, J. Nash Q-learning for general-sum stochastic games / J. Hu, M. P. Wellman // Machine Learning Research. – 2003. – No. 4. – PP. 1039 – 1069.
Wooldridge M. An Introduction to Multiagent Systems / M. Wooldridge. – John Wiley & Sons, 2002. – 366 pp.
Weiss, G. Multiagent Systems. A Modern Approach to Distributed Artificial Intelligence / G. Weiss, editor. – Springer Verlag, Berlin, 1996. – 643 pp.
Назин А.В. Адаптивный выбор вариантов: Рекуррентные алгоритмы / А.В. Назин, А.С. Позняк. – М.: Наука, 1986. – 288 с.
Kaelbling, Leslie. Reinforcement learning: A survey / Leslie Kaelbling, Michael L. Littman, Andrew W. Moore. Journal of Artificial Intelligence Research. – 1996. – No. 4. – PP. 237–285.
Sutton, R. S. Reinforcement Learning: An Introduction / Richard S. Sutton, Andrew G. Barto. – MIT Press, 1998. – 322 pp.
Musiyenko М., Zhuravska І., Kulakovska І., Kulakovska А. Simulation the behavior of robot sub swarm in spatial corridors. 2016 IEEE 36th ELNANO. April 19-21, 2016. Kyiv, Ukraine. Page(s) 382-387. DOI:
10.1109/ELNANO.2016.7493090 http://ieeexplore.ieee.org/document/7493090/
Published
2020-01-23
How to Cite
Asieiev , V., & Kulakovska, I. (2020). Modeling agents strategies in players with local interaction. COMPUTER-INTEGRATED TECHNOLOGIES: EDUCATION, SCIENCE, PRODUCTION, (35), 10-15. Retrieved from https://cit.lntu.edu.ua/index.php/cit/article/view/51
Section
Automation and Control
