MAT3.0

Mutli-Agent Toolkit (MAT) 3.0 presents a set of toolboxes, implemented with MATLAB, that we developed for conducting research studies related to multi-agent and multi-robot reinforcement learning, adaptation, se- lf-organization, trajectory generation, and graphics. The toolboxes i- nclude: Multi-Agent Reinforcement Learning Evolutionary Multi-Agent Reinforcement Learning Evolutionary Collective Behavior Implementation Multi-Agent Self-Organization Evolutionary Multi-Agent Self-Organization These toolboxes are useful for simulation as well as for analyzing re- sults of experiments with simulated robots. They are based on a very general method of representing the evolutionary approaches to multi- agent robotic systems by description matrices. Note that MAT 3.0 Copyright is reserved. Any using, addition, and modi- fication should be acknowledged to the authors (jiming@comp.hkbu.edu.hk).