Deep Imitation Learning on Spatio-Temporal Data with Multiple Adversarial Agents Applied on Soccer
Recently, the availability of high quality and high resolution spatio-temporal data has increased for many sports. This enabled deep analysis of player behaviour and game strategy. This thesis investigates the assumption that game strategy is latent information in tracking data from soccer games and...
| Main Author: | |
|---|---|
| Format: | Others |
| Language: | English |
| Published: |
Linköpings universitet, Databas och informationsteknik
2019
|
| Subjects: | |
| Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-158076 |