Timezone: »

 
Poster
Learning Agent Representations for Ice Hockey
Guiliang Liu · Oliver Schulte · Pascal Poupart · Mike Rudd · Mehrsan Javan

Wed Dec 09 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1240
in Poster Session 5 »

Team sports is a new application domain for agent modeling with high real-world impact. A fundamental challenge for modeling professional players is their large number (over 1K), which includes many bench players with sparse participation in a game season. The diversity and sparsity of player observations make it difficult to extend previous agent representation models to the sports domain. This paper develops a new approach for agent representations, based on a Markov game model, that is tailored towards applications in professional ice hockey. We introduce a novel player representation via player generation framework where a variational encoder embeds player information with latent variables. The encoder learns a context-specific shared prior to induce a shrinkage effect for the posterior player representations, allowing it to share statistical information across players with different participations. To model the play dynamics in sequential sports data, we design a Variational Recurrent Ladder Agent Encoder (VaRLAE). It learns a contextualized player representation with a hierarchy of latent variables that effectively prevents latent posterior collapse. We validate our player representations in major sports analytics tasks. Our experimental results, based on a large dataset that contains over 4.5M events, show state-of-the-art performance for our VarLAE on facilitating 1) identifying the acting player, 2) estimating expected goals, and 3) predicting the final score difference.

Author Information

Guiliang Liu (Simon Fraser University)
Oliver Schulte (Simon Fraser University)
Oliver Schulte

Bio: Oliver Schulte is a Professor in the School of Computing Science at Simon Fraser University, Vancouver, Canada. He received his Ph.D. from Carnegie Mellon University in 1997. His current research focuses on machine learning for structured, relational, and event data. He has published sports analytics papers in leading AI and machine learning venues, and co-organized two hockey analytics conferences. The last two years he has worked with Sportlogiq, a leading hockey data provider. While he has won some nice awards, his biggest claim to fame may be a draw against chess world champion Gary Kasparov.

Pascal Poupart (University of Waterloo & Vector Institute)
Mike Rudd (University of Waterloo)
Mehrsan Javan (SPORTLOGiQ)

Mehrsan Javan, PhD, MBA, is the co-founder and CTO of SPORTLOGiQ, the AI platform for sport analytics that provides real-time game insights to the professional leagues and media broadcasters using feeds from a single broadcast camera. He holds a PhD degree in computer vision and machine learning with over a decade of experience in building intelligent systems. At SPORTLOGiQ, he is responsible for tech development and the planning of strategic research to build future technologies and products. His passion is new technologies with a particular interest in intelligent systems and their positive impacts on our daily life. He is also an adjunct faculty member at ECE department, McGill University and has published numerous research articles in top tier journals and conferences which have been cited more than 850 times and holds several patents and patent pending applications.

More from the Same Authors