Evaluating Soccer Player: from Live Camera to Deep Reinforcement Learning
This addresses the challenge of scientifically evaluating soccer players for sports analysts and teams, offering a novel simulation-based method that bypasses data scarcity issues.
The paper tackles the problem of evaluating soccer players by introducing a two-part solution: an open-source Player Tracking model and a Deep Reinforcement Learning-based evaluation method called Expected Discounted Goal (EDG), which uses simulations to assess players without human data, achieving more meaningful results than existing real-world data approaches.
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.