Download Multi Agent Machine Learning A Reinforcement Approach by Howard M. Schwartz easily in PDF format for free.

For a decade I have taught a course on adaptive control. The course focused on the classical methods of system identification, using such classic texts as Ljung [1, 2]. The course addressed traditional methods of model reference adaptive control and nonlinear adaptive control using Lyapunov techniques. However, the theory had become out of sync with current engineering practice.

As such, my own research and the focus of the graduate course changed to include adaptive signal processing, and to incorporate adaptive channel equalization and echo cancellation using the least mean squares (LMS) algorithm. The course name likewise changed, from “Adaptive Control” to “Adaptive and Learning Systems.” My research was still focused on system identification and nonlinear adaptive control with application to robotics.

However, by the early 2000s, I had started work with teams of robots. It was now possible to use handy robot kits and low-cost microcontroller boards to build several robots that could work together. The graduate course in adaptive and learning systems changed again; the theoretical material on nonlinear adaptive control using Lyapunov techniques was reduced, replaced with ideas from reinforcement learning.

A whole new range of applications developed. The teams of robots had to learn to work together and to compete. Today, the graduate course focuses on system identification using recursive least squares techniques, some model reference adaptive control (still using Lyapunov techniques), adaptive signal processing using the LMS algorithm, and reinforcement learning using Q-learning.

The first two chapters of this book present these ideas in an abridged form, but in sufficient detail to demonstrate the connections among the learning algorithms that are available; how they are the same; and how they are different. There are other texts that cover this material in detail [2–4]. The research then began to focus on teams of robots learning to work together.

The work examined applications of robots working together for search and rescue applications, securing important infrastructure and border regions. It also began to focus on reinforcement learning and multiagent reinforcement learning. The robots are the learning agents. How do children learn how to play tag? How do we learn to play football, or how do police work together to capture a criminal?