Deep Learning Based Player Identification Via Behavioral Characteristics
DOI:
https://doi.org/10.54097/hset.v61i.10732Keywords:
Player’s behavioral, CNN, LSTM, Multivariate.Abstract
Behavioral recognition in game is a fundamental topic in data analysis. With the emerging of deep learning-based method, more and more artificial neural networks are proposed to achieve higher accuracy and robustness. This paper presents a comparison between CNN and RNN-LSTM for player identification based on player behavioral characteristics in a simple game environment. The goal is to detect potential manual cheating in competitions by recognizing unidentified players (cheaters) from their behavioral patterns. We implement a basic game, record player behaviors, and then compare the accuracy of outputs from the CNN and RNN-LSTM models. The conclusion is summarized as follow. CNN obtains 87.5% accuracy and RNN-LSTM achieves 92.3% accuracy in the simulated data. Our results indicate that the RNN-LSTM model outperforms the CNN model in terms of accuracy, making it a more suitable choice for player identification in this contextt.
Downloads
References
Samuel A L. “Some studies in machine learning using the game of checkers”, IBM Journal of research and development, 1959, 3(3): 210-229.
Tesauro G. “Temporal difference learning and TD-Gammon”, Communications of the ACM, 1995, 38(3): 58-68.
Gelly S, Kocsis L, Schoenauer M, et al. “The grand challenge of computer Go: Monte Carlo tree search and extensions”, Communications of the ACM, 2012, 55(3): 106-113.
Drachen, A., Canossa, A., & Yannakakis, G. N., “Player Modeling using Self-Organization in Tomb Raider: Underworld”. Proceedings of the IEEE Symposium on Computational Intelligence and Games, 1-8 (2009).
Krizhevsky, A., Sutskever, I., & Hinton, G. E.,“ImageNet Classification with Deep Convolutional Neural Networks”. Advances in Neural Information Processing Systems, 25, 1097-1105, (2012).
Khan, G. M. A., Zang, P., & Sohail, S., “A Comprehensive Survey on Deep Learning-based Methodologies for Game AI”. IEEE Transactions on Games, 12(1), 1-16 (2017).
Hochreiter, S., & Schmidhuber, J., “Long Short-Term Memory. Neural Computation”, 9(8), 1735-1780 (1997).
Gers, F. A., Schmidhuber, J., & Cummins, F., “Learning to Forget: Continual Prediction with LSTM”. Neural Computation, 12(10), 2451-2471 (2000).
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P., “Gradient-Based Learning Applied to Document Recognition”. Proceedings of the IEEE, 86(11), 2278-2324, (1998).
Zhang, S., Zhao, Y., & Lu, B., “A Deep Reinforcement Learning Based Approach to Model Player Behaviors in Fighting Games”. Proceedings of the IEEE Conference on Games, 1-8 (2018).
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
