Abstract
Analyzing and understanding strategies applied by top soccer teams has always been in the focus of coaches, scouts, players, and other sports professionals. Although the game strategies can be quite complex, we focus on the offensive or defensive approaches that need to be adopted by the coach before or throughout the match. In order to build interpretable parameterizations of soccer decision making, we propose a batch gradient inverse reinforcement learning for modeling the teams’ reward function in terms of offense or defense. Our conducted experiments on soccer logs made by Wyscout company on German Bundesliga reveal two important facts: the highest-ranked teams are planning strategically for offense and defense before the match with the largest weights on pre-match features; the lowest-ranked teams apply short-term planning with larger weights on in-match features.
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
Baxter, J., Bartlett, P.L.: Infinite-horizon policy-gradient estimation. J. Artif. Intell. Res. 15, 319–350 (2001)
Decroos, T., Bransen, L., Van Haaren, J., Davis, J.: Actions speak louder than goals: valuing player actions in soccer. In: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2019) (2019)
Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. CoRR abs/1411.4389 (2014)
Fernández, J., Bornn, L.: SoccerMap: a deep learning architecture for visually-interpretable analysis in soccer. In: Dong, Y., Ifrim, G., Mladenić, D., Saunders, C., Van Hoecke, S. (eds.) ECML PKDD 2020, Part V. LNCS (LNAI), vol. 12461, pp. 491–506. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67670-4_30
Fernandez, J., Bornn, L., Cervone, D.: Decomposing the immeasurable sport: a deep learning expected possession value framework for soccer. In: In Proceedings of the 13th MIT Sloan Sports Analytics Conference (2019)
Fernandez-Navarro, J.: Analysis of styles of play in soccer and their effectiveness. Ph.D. thesis, Universidad de Granada (2018)
Fernandez-Navarro, J., Fraduab, L., Zubillagac, A., Forda, P.R., McRobert, A.P.: Attacking and defensive styles of play in soccer: analysis of Spanish and English elite teams. J. Sports Sci. 34, 1–10 (2016)
Gambarelli, D., Gambarelli, G., Goossens, D.: Offensive or defensive play in soccer: a game-theoretical approach. J. Quant. Anal. Sports 15(4), 261–269 (2019)
Gyarmati, L., Stanojevic, R.: QPass: a merit-based evaluation of soccer passes (2016)
Hirotsu, N., Wright, M.: Modeling tactical changes of formation in association football as a zero-sum game. J. Quant. Anal. Sports 2(2), 1–15 (2006)
Inna, Z., Daniil, S.: Moneyball in offensive vs defensive actions in soccer. Eur. Econ. Labor Soc. Cond. eJournal (2020)
Liu, G., Luo, Y., Schulte, O., Kharrat, T.: Deep soccer analytics: learning an action-value function for evaluating soccer players. Data Min. Knowl. Discov. 34(5), 1531–1559 (2020). https://doi.org/10.1007/s10618-020-00705-9
Liu, G., Schulte, O.: Deep reinforcement learning in ice hockey for context-aware player evaluation. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) (2018)
Luo, Y., Schulte, O., Poupart, P.: Inverse reinforcement learning for team sports: valuing actions and players. In: Bessiere, C. (ed.) Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, pp. 3356–3363 (2020)
Metelli, A.M., Pirotta, M., Restelli, M.: Compatible reward inverse reinforcement learning. In: The Thirty-first Annual Conference on Neural Information Processing Systems (2017)
Muelling, K., Boularias, A., Mohler, B., Schoelkopf, B., Peters, J.: Inverse reinforcement learning for strategy extraction. In: ECML PKDD 2013 Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA 2013) (2013)
Peralta Alguacil, F., Fernandez, J., Piñones Arce, P., Sumpter, D.: Seeing in to the future: using self-propelled particle models to aid player decision-making in soccer. In: Proceedings of the 14th MIT Sloan Sports Analytics Conference (2020)
Pirotta, M., Restelli, M.: Inverse reinforcement learning through policy gradient minimization. In: AAAI (2016)
Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, Hoboken (1994)
Tateo, D., Pirotta, M., Restelli, M., Bonarini, A.: Gradient-based minimization for multi-expert inverse reinforcement learning. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1–8 (2017)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229–256 (1992)
Zaytseva, I., Shaposhnikov, D.: Moneyball in offensive vs defensive actions in soccer. Eur. Econ. Labor Soc. Cond. eJournal (2020)
Acknowledgment
Project no. 128233 has been implemented with the support provided by the Ministry of Innovation and Technology of Hungary from the National Research, Development and Innovation Fund, financed under the FK_18 funding scheme.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rahimian, P., Toka, L. (2022). Inferring the Strategy of Offensive and Defensive Play in Soccer with Inverse Reinforcement Learning. In: Brefeld, U., Davis, J., Van Haaren, J., Zimmermann, A. (eds) Machine Learning and Data Mining for Sports Analytics. MLSA 2021. Communications in Computer and Information Science, vol 1571. Springer, Cham. https://doi.org/10.1007/978-3-031-02044-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-02044-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02043-8
Online ISBN: 978-3-031-02044-5
eBook Packages: Computer ScienceComputer Science (R0)