Систем за адаптацију стратегије у поновљеним неодређеним играма нулте суме са два играча

Đorđe Mirosavić

doi:10.24867/

Electrotechnical and Computer Engineering

Vol. 41 No. 08 (2026): Proceedings of the Faculty of Technical Sciences

System for Strategy Adaptation in Repeated Two-Player Zero-Sum Uncertain Games

Djordje Mirosavic

PDF (Serbian)

DOI:: https://doi.org/10.24867/
Submitted: September 7, 2026
Published: 2026-09-09

Abstract

The topic of this paper is the creation of a platform that learns human behavior in the game rockpaper-scissors and, accordingly, adaptively selects a strategy to defeat them. The first part of the paper will present the strategies to be used, and the development of the software and hardware platform. The second part will present the results of the experiments.

References

[1] Figurska M, Stańczyk M, Kulesza K. (2008).
“Humans cannot consciously generate random
numbers sequences: Polemic study”
[2] Schulz, MA., Baier, S., Timmermann, B. (2021). “A
cognitive fingerprint in human random number
generation”
[3] Hasselt, H., Guez, A., & Silver, D. (2015). “Deep
Reinforcement Learning with Double Q-learning”
[4] Wang, Z., Xu, B. & Zhou, HJ. (2014).“Social cycling
and conditional responses in the Rock-Paper-Scissors
game”
[5] Kumar, D. (2024).“DDQN: Tackling Overestimation
Bias in Deep Reinforcement Learning”

[1] [1] Figurska M, Stańczyk M, Kulesza K. (2008).

[2] “Humans cannot consciously generate random

[3] numbers sequences: Polemic study”

[4] [2] Schulz, MA., Baier, S., Timmermann, B. (2021). “A

[5] cognitive fingerprint in human random number

[6] generation”

[7] [3] Hasselt, H., Guez, A., & Silver, D. (2015). “Deep

[8] Reinforcement Learning with Double Q-learning”

[9] [4] Wang, Z., Xu, B. & Zhou, HJ. (2014).“Social cycling

[10] and conditional responses in the Rock-Paper-Scissors

[11] game”

[12] [5] Kumar, D. (2024).“DDQN: Tackling Overestimation

[13] Bias in Deep Reinforcement Learning”