Reinforcement Learning for Cooperating and Communicating Reactive Agents in Electrical Power Grids (2001)

Martin Riedmiller, Andrew Moore, Jeff Schneider

Tags

Applications, Markov Decision Processes, Optimization, Reinforcement Learning

Abstract

Social behaviour in intelligent agent systems is often considered to be achieved by deliberative, in-depth reasoning techniques. This paper shows, how a purely reactive multi-agent system can learn to evolve cooperative behaviour, by means of learning from previous experiences. In particular, we describe a learning multi-agent approach to the problem of controlling power flow in an electrical power-grid. The problem is formulated within the framework of dynamic programming. Via a global optimization goal, a set of individual agents is forced to autonomously learn to cooperate and communicate. The ability of the purely reactive distributed systems to solve the global problem by means of establishing a communication mechanism is shown on two prototypical network configurations.

Full text

Download (application/pdf, 176.4 kB)

Approximate BibTeX Entry

@incollection{riedmiller-reinforcement,
    Year = {2001},
    Publisher = {Springer},
    Booktitle = {Balancing Reactivity and Social Deliberation in Multi-Agent Systems},
    Editor = { Markus Hannebauer, Jan Wendler, Enrico},
    Author = { Martin Riedmiller, Andrew Moore, Jeff Schneider },
    Title = {Reinforcement Learning for Cooperating and Communicating Reactive Agents in Electrical Power Grids}
}