Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
EN  |  EL

Αναζήτηση

Πλοήγηση

Ο Χώρος μου

Optimising long-term outcomes using real-world fluent objectives: an application to football

Beal Ryan J., Chalkiadakis Georgios, Norman Timothy J., Ramchurn, Sarvapali Dyanand

Απλή Εγγραφή


URIhttp://purl.tuc.gr/dl/dias/6714C84A-92A6-489A-B263-2B0EC8C7DC9F-
Αναγνωριστικόhttps://doi.org/10.48550/arXiv.2102.09469-
Αναγνωριστικόhttps://arxiv.org/abs/2102.09469-
Αναγνωριστικόhttps://dl.acm.org/doi/10.5555/3463952.3463981 -
Γλώσσαen-
Μέγεθος9 pagesen
ΤίτλοςOptimising long-term outcomes using real-world fluent objectives: an application to footballen
ΔημιουργόςBeal Ryan J.en
ΔημιουργόςChalkiadakis Georgiosen
ΔημιουργόςΧαλκιαδακης Γεωργιοςel
ΔημιουργόςNorman Timothy J.en
ΔημιουργόςRamchurn, Sarvapali Dyananden
ΕκδότηςInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)en
ΠερίληψηIn this paper, we present a novel approach for optimising longterm tactical and strategic decision-making in football (soccer) by encapsulating events in a league environment across a given time frame. We model the teams’ objectives for a season and track how these evolve as games unfold to give a fluent objective that can aid in decision-making games. We develop Markov chain Monte Carlo and deep learning-based algorithms that make use of the fluent objectives in order to learn from prior games and other games in the environment and increase the teams’ long-term performance. Simulations of our approach using real-world datasets from 760 matches shows that by using optimised tactics with our fluent objective and prior games, we can on average increase teams mean expected finishing distribution in the league by up to 35.6%.en
ΤύποςΔημοσίευση σε Συνέδριοel
ΤύποςConference Publicationen
Άδεια Χρήσηςhttp://creativecommons.org/licenses/by/4.0/en
Ημερομηνία2023-07-13-
Ημερομηνία Δημοσίευσης2021-
Θεματική ΚατηγορίαArtificial intelligenceen
Θεματική ΚατηγορίαComputer science and game theoryen
Βιβλιογραφική ΑναφοράR. Beal, G. Chalkiadakis, T. J. Norman, and S. D. Ramchurn, “Optimising long-term outcomes using real-world fluent objectives: an application to football,” in Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), virtual event, 2021, vol. 1, pp. 196-204, doi: 10.48550/arXiv.2102.09469.en

Υπηρεσίες

Στατιστικά