What is the value of an action in ice hockey? Learning a Q-function for the NHL
Recent work has applied the Markov Game formalism from AI to model game dynamics for ice hockey, using a large state space. Dynamic programming is used to learn action-value functions that quantify the impact of actions on goal scoring. Learning is based on a massive dataset that contains over 2.8M events in the National Hockey League. As an application of the Markov model, we use the learned action values to measure the impact of player actions on goal scoring. Players are ranked according to the aggregate goal impact of their actions. We show that this ranking is consistent across seasons, and compare it with previous player metrics, such as plus-minus and total points.
© Copyright 2015 Machine Learning and Data Mining for Sports Analytics ECML/PKDD 2015 workshop. Julkaistu Tekijä Department of Computer Science, KU Leuven. Kaikki oikeudet pidätetään.
Aiheet: | kilpailu jääkiekko matemaattis-looginen malli tilastomatematiikka tietokanta analyysi taktiikka yksilöllinen |
---|---|
Aihealueet: | tekniset ja luonnontieteet urheilukilpailut |
Tagging: | data mining |
Julkaisussa: | Machine Learning and Data Mining for Sports Analytics ECML/PKDD 2015 workshop |
Toimittajat: | J. Van Haaren, A. Zimmermann, J. Davis |
Julkaistu: |
Leuven
Department of Computer Science, KU Leuven
2015
|
Sivuja: | 75-84 |
Julkaisutyypit: | artikkeli |
Kieli: | englanti (kieli) |
Taso: | kehittynyt |