DeepAI AI Chat
Log In Sign Up

Improved Structural Discovery and Representation Learning of Multi-Agent Data

by   Jennifer Hobbs, et al.

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.


Learning to Coordinate via Multiple Graph Neural Networks

The collaboration between agents has gradually become an important topic...

Deep Reinforcement Learning for Multi-Agent Interaction

The development of autonomous agents which can interact with other agent...

Deep Decision Trees for Discriminative Dictionary Learning with Adversarial Multi-Agent Trajectories

With the explosion in the availability of spatio-temporal tracking data ...

Information-Bottleneck-Based Behavior Representation Learning for Multi-agent Reinforcement learning

In multi-agent deep reinforcement learning, extracting sufficient and co...

Distributed Possibilistic Learning in Multi-Agent Systems

Possibility theory is proposed as an uncertainty representation framewor...

Set-to-Sequence Methods in Machine Learning: a Review

Machine learning on sets towards sequential output is an important and u...

Fine-Grained Retrieval of Sports Plays using Tree-Based Alignment of Trajectories

We propose a novel method for effective retrieval of multi-agent spatiot...