Abstract
Convolutional Neural Network (CNN) is a fundamental tool in Deep Learning and Computer Vision due to its remarkable ability to extract relevant characteristics from raw data, which has been allowing significant advances in image classification tasks. One of the great challenges in using CNNs is to define an architecture that is suitable for the problem for which they are being designed. Thus, there is a big effort in many recent works to propose approaches to automatically define appropriate CNN architectures. Among them, the Convolutional Neural Network designed by Genetic Algorithm (CNN-GA) method stands out. As CNN-GA has only been validated in static scenarios involving image classification data sets, the main contributions of the present paper are the following: implementing an improved version of CNN-GA, named as Minimum CNN-GA (MCNN-GA), that automatically defines CNN architectures through a policy that minimizes the weigh vector dimensions and the classification error rate of the CNNs; implementing a set of imitation learning based agents that operate in a complex and dynamic scenario of FIFA game exploring distinct raw image representations for the environment at the input of CNNs designed according to the MCNN-GA approach. The performance of these agents were evaluated through their in-game score in tournaments against FIFA’s engine. The results corroborate that the decision-making ability of such agents can be as good as human ability.
The authors thank CAPES for financial support.
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
Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. In: 5th International Conference on Learning Representations (2017)
Buche, C., Even, C., Soler, J.: Autonomous virtual player in a video game imitating human players: the orion framework. In: 2018 International Conference on Cyberworlds, pp. 108–113 (2018)
Coleman, A.M.: A Dictionary of Psychology, 3rd edn. Oxford University Press, Oxford (2009)
Faria, M.P.P., Julia, R.M.S., Tomaz, L.B.P.: Evaluating the performance of the deep active imitation learning algorithm in the dynamic environment of FIFA player agents. In: 18th IEEE International Conference on Machine Learning and Applications (2019)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, New York (2016). http://www.deeplearningbook.org
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (2016)
Hussein, A., Elyan, E., Gaber, M.M., Jayne, C.: Deep imitation learning for 3D navigation tasks. Neural Comput. Appl. 29, 389–404 (2018)
Hussein, A., Gaber, M.M., Elyan, E., Jayne, C.: Imitation learning: a survey of learning methods. ACM Comput. Surv. 50, 21:1–21:35 (2017)
Justesen, N., Bontrager, P., Togelius, J., Risi, S.: Deep learning for video game playing. IEEE Trans. Games 12, 1–20 (2020)
Krizhevsky, A., Nair, V., Hinton, G.: CIFAR-10 and CIFAR-100 (Canadian institute for advanced research). http://www.cs.toronto.edu/~kriz/cifar.html
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097–1105. Curran Associates, Inc. (2012)
LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521, 436–444 (2015)
Liu, H., Simonyan, K., Vinyals, O., Fernando, C., Kavukcuoglu, K.: Hierarchical representations for efficient architecture search (2018)
Liu, W., Wang, Z., Liu, X., Zeng, N., Liu, Y., Alsaadi, F.E.: A survey of deep neural network architectures and their applications. Neurocomputing 234, 11–26 (2017)
Liu, Y., Gupta, A., Abbeel, P., Levine, S.: Imitation from observation: learning to imitate behaviors from raw video via context translation. In: 2018 IEEE International Conference on Robotics and Automation, pp. 1118–1125 (2018)
Miller, B.L., Miller, B.L., Goldberg, D.E., Goldberg, D.E.: Genetic algorithms, tournament selection, and the effects of noise. Complex Syst. 9, 193–212 (1995)
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)
Real, E., et al.: Large-scale evolution of image classifiers. In: Proceedings of the 34th International Conference on Machine Learning, Vol. 70, pp. 2902–2911 (2017)
Refaeilzadeh, P., Tang, L., Liu, H.: Cross-validation. In: Liu, L., Özsu, M.T. (eds.) Encyclopedia of Database Systems, pp. 532–538. Springer, Boston (2009). https://doi.org/10.1007/978-0-387-39940-9
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 3rd edn. Prentice Hall Press, Upper Saddle River (2009)
Sammut, C., Webb, G.I.: Holdout evaluation. In: Encyclopedia of Machine Learning, pp. 506–507. Springer, Boston (2010). https://doi.org/10.1007/978-0-387-30164-8_369
Srinivas, M., Patnaik, L.M.: Genetic algorithms: a survey. Computer 27, 17–26 (1994)
Sun, Y., Xue, B., Zhang, M., Yen, G.G., Lv, J.: Automatically designing CNN architectures using the genetic algorithm for image classification. IEEE Trans. Cybern. 50(9), 1–15 (2020)
Xie, L., Yuille, A.: Genetic CNN. In: 2017 IEEE International Conference on Computer Vision, pp. 1388–1397 (2017)
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: International Conference on Learning Representations (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
Faria, M.P.P., Julia, R.M.S., Tomaz, L.B.P. (2020). Improving FIFA Player Agents Decision-Making Architectures Based on Convolutional Neural Networks Through Evolutionary Techniques. In: Cerri, R., Prati, R.C. (eds) Intelligent Systems. BRACIS 2020. Lecture Notes in Computer Science(), vol 12319. Springer, Cham. https://doi.org/10.1007/978-3-030-61377-8_26
Download citation
DOI: https://doi.org/10.1007/978-3-030-61377-8_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61376-1
Online ISBN: 978-3-030-61377-8
eBook Packages: Computer ScienceComputer Science (R0)