MagNet: Discovering Multi-agent Interaction Dynamics using Neural Network

01/24/2020
by   Priyabrata Saha, et al.
0

We present the MagNet, a multi-agent interaction network to discover governing dynamics and predict evolution of a complex system from observations. We formulate a multiagent 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/01/2021

Design of heterogeneous multi-agent system for distributed computation

A group behavior of a heterogeneous multi-agent system is studied which ...
research
05/04/2019

Model reconstruction from temporal data for coupled oscillator networks

In a complex system, the interactions between individual agents often le...
research
04/02/2018

A Tool for Analysis and Synthesis of Heterogeneous Multi-agent Systems under Rank-deficient Coupling

The behavior of heterogeneous multi-agent systems is studied when the co...
research
09/14/2022

An ensemble Multi-Agent System for non-linear classification

Self-Adaptive Multi-Agent Systems (AMAS) transform machine learning prob...
research
04/29/2009

Continuous Strategy Replicator Dynamics for Multi--Agent Learning

The problem of multi-agent learning and adaptation has attracted a great...
research
07/13/2023

Discovering How Agents Learn Using Few Data

Decentralized learning algorithms are an essential tool for designing mu...
research
10/28/2022

Forecasting local behavior of multi-agent system and its application to forest fire model

In this paper, we study a CNN-LSTM model to forecast the state of a spec...

Please sign up or login with your details

Forgot password? Click here to reset