Fully Distributed Learning for Global Optima

8.1    Introduction

In the previous chapters, we have studied equilibrium-seeking procedures. In this chapter, we focus on distributed strategic learning for global optima in specific classes of games.

In many problems, distributed strategic learning may have a tendency to converge toward local optima or even arbitrary points rather than the global optimum of the problem. This means that it does not ”know how” to sacrifice short-term payoff to gain a longer-term payoff. The likelihood of this occurring depends on the shape of the payoff functions. Certain problems may provide an easy ascent towards a global optimum, whereas others may make it easier for the function to find the local optima. ...

Get Distributed Strategic Learning for Wireless Engineers now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.