# Evaluating Soccer Player: from Live Camera to Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2101.05388 · HTML: https://mlsanity.com/paper/2101.05388/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 13 Jan 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Google Research Football: A Novel Reinforcement Learning Environment](https://mlsanity.com/paper/1907.11180/) (2019)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Deep Homography Estimation for Dynamic Scenes](https://mlsanity.com/paper/2004.02132/) (2020)
- [GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing](https://mlsanity.com/paper/1907.04433/) (2019)
- [Detecting events and key actors in multi-person videos](https://mlsanity.com/paper/1511.02917/) (2015)
- [Sports Camera Calibration via Synthetic Data](https://mlsanity.com/paper/1810.10658/) (2018)
- [Optimizing Through Learned Errors for Accurate Sports Field Registration](https://mlsanity.com/paper/1909.08034/) (2019)
- [Real-Time Camera Pose Estimation for Sports Fields](https://mlsanity.com/paper/2003.14109/) (2020)
- [Automated Top View Registration of Broadcast Football Videos](https://mlsanity.com/paper/1703.01437/) (2017)

## Built on by (most cited first, 4 of 4)

- [A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directions](https://mlsanity.com/paper/2203.02281/) (2022)
- [How does AI play football? An analysis of RL and real-world football strategies](https://mlsanity.com/paper/2111.12340/) (2021)
- [Expected Possession Value of Control and Duel Actions for Soccer Player's Skills Estimation](https://mlsanity.com/paper/2406.00814/) (2024)
- [Calisthenics Skills Temporal Video Segmentation](https://mlsanity.com/paper/2507.12245/) (2025)

## Abstract (arXiv)

Scientifically evaluating soccer players represents a challenging Machine Learning problem. Unfortunately, most existing answers have very opaque algorithm training procedures; relevant data are scarcely accessible and almost impossible to generate. In this paper, we will introduce a two-part solution: an open-source Player Tracking model and a new approach to evaluate these players based solely on Deep Reinforcement Learning, without human data training nor guidance. Our tracking model was trained in a supervised fashion on datasets we will also release, and our Evaluation Model relies only on simulations of virtual soccer games. Combining those two architectures allows one to evaluate Soccer Players directly from a live camera without large datasets constraints. We term our new approach Expected Discounted Goal (EDG), as it represents the number of goals a team can score or concede from a particular state. This approach leads to more meaningful results than the existing ones that are based on real-world data, and could easily be extended to other sports.