Learning in traffic control: adaptive processes and EAMs

The fundamentals of our approach are that every action undertaken by a (sub)agent is an act of control; and hence is contained in an adaptive loop. We present a number of elementary adaptive modules (EAMs), the basic building blocks of adaptive agent systems, with a discussion of their use, their control, and their behaviors under different conditions; we also discuss the host of problems that we expect to run into. We apply these ideas to a model of traffic control by agents that run vehicles and control traffic lights