Improved Structural Discovery and Representation Learning of Multi-Agent Data
arXiv:1912.13107
Abstract
Central to all machine learning algorithms is data representation. For multi-agent systems, selecting a representation which adequately captures the interactions among agents is challenging due to the latent group structure which tends to vary depending on context. However, in multi-agent systems with strong group structure, we can simultaneously learn this structure and map a set of agents to a consistently ordered representation for further learning. In this paper, we present a dynamic alignment method which provides a robust ordering of structured multi-agent data enabling representation learning to occur in a fraction of the time of previous methods. We demonstrate the value of this approach using a large amount of soccer tracking data from a professional league.
References in corpus (6)
- Interaction Networks for Learning about Objects, Relations and Physics
- Neural Relational Inference for Interacting Systems
- Ranking via Sinkhorn Propagation
- Generating Long-term Trajectories Using Deep Hierarchical Networks
- Coordinated Multi-Agent Imitation Learning
- Fine-Grained Retrieval of Sports Plays using Tree-Based Alignment of Trajectories