DeepAI AI Chat
Log In Sign Up

Memory-like Adaptive Modeling Multi-Agent Learning System

by   Xingyu Qian, et al.

In this work, we propose a self-supervised multi-agent system, termed a memory-like adaptive modeling multi-agent learning system (MAMMALS), that realizes online learning towards behavioral pattern clustering tasks for time series. Encoding the visual behaviors as discrete time series(DTS), and training and modeling them in the multi-agent system with a bio-memory-like form. We finally implemented a fully decentralized multi-agent system design framework and completed its feasibility verification in a surveillance video application scenario on vehicle path clustering. In multi-agent learning, using learning methods designed for individual agents will typically perform poorly globally because of the behavior of ignoring the synergy between agents.


page 1

page 2

page 3

page 4


VAIN: Attentional Multi-agent Predictive Modeling

Multi-agent predictive modeling is an essential step for understanding p...

Multi-Agent Interactions Modeling with Correlated Policies

In multi-agent systems, complex interacting behaviors arise due to the h...

Modeling MOOC learnflow with Petri net extensions

Modern higher education takes advantage of MOOC technology. Modeling an ...

A Formal Framework for Reasoning about Agents' Independence in Self-organizing Multi-agent Systems

Self-organization is a process where a stable pattern is formed by the c...

Multi-agent Searching System for Medical Information

In the paper is proposed a model of multi-agent security system for sear...

Efficient Calibration of Multi-Agent Market Simulators from Time Series with Bayesian Optimization

Multi-agent market simulation is commonly used to create an environment ...

Learning Nested Agent Models in an Information Economy

We present our approach to the problem of how an agent, within an econom...