MagNet: Discovering Multi-agent Interaction Dynamics using Neural Network
This work addresses the challenge of modeling multi-agent interactions for applications like robotics or physics simulations, though it appears incremental as it builds on existing neural network approaches.
The paper tackles the problem of predicting the evolution of complex multi-agent systems by introducing MagNet, a neural network-based model that discovers governing dynamics from observations, achieving orders of magnitude improvement in prediction accuracy over traditional deep learning models.
We present the MagNet, a neural network-based multi-agent interaction model to discover the governing dynamics and predict evolution of a complex multi-agent system from observations. We formulate a multi-agent system as a coupled non-linear network with a generic ordinary differential equation (ODE) based state evolution, and develop a neural network-based realization of its time-discretized model. MagNet is trained to discover the core dynamics of a multi-agent system from observations, and tuned on-line to learn agent-specific parameters of the dynamics to ensure accurate prediction even when physical or relational attributes of agents, or number of agents change. We evaluate MagNet on a point-mass system in two-dimensional space, Kuramoto phase synchronization dynamics and predator-swarm interaction dynamics demonstrating orders of magnitude improvement in prediction accuracy over traditional deep learning models.