Deep Decision Trees for Discriminative Dictionary Learning with Adversarial Multi-Agent Trajectories
This work addresses the analysis of group dynamics in adversarial environments like sports, offering an interpretable method for learning from spatio-temporal data, but it is incremental as it builds on existing dictionary learning and decision tree techniques.
The paper tackles the problem of analyzing adversarial multi-agent trajectories in sports by proposing a deep decision tree architecture for discriminative dictionary learning, which captures group interactions and is applied to soccer tracking data for simulating games and evaluating team strategies.
With the explosion in the availability of spatio-temporal tracking data in modern sports, there is an enormous opportunity to better analyse, learn and predict important events in adversarial group environments. In this paper, we propose a deep decision tree architecture for discriminative dictionary learning from adversarial multi-agent trajectories. We first build up a hierarchy for the tree structure by adding each layer and performing feature weight based clustering in the forward pass. We then fine tune the player role weights using back propagation. The hierarchical architecture ensures the interpretability and the integrity of the group representation. The resulting architecture is a decision tree, with leaf-nodes capturing a dictionary of multi-agent group interactions. Due to the ample volume of data available, we focus on soccer tracking data, although our approach can be used in any adversarial multi-agent domain. We present applications of proposed method for simulating soccer games as well as evaluating and quantifying team strategies.