论文信息 - Reinforcement Learning for Cooperating and Communicating Reactive Agents in Electrical Power Grids

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

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.

Andrew W. Moore | Jeff G. Schneider | Martin A. Riedmiller | A. Moore | J. Schneider

[1] Ben J. A. Kröse,et al. Learning from delayed rewards , 1995, Robotics Auton. Syst..

[2] Andrew G. Barto,et al. Improving Elevator Performance Using Reinforcement Learning , 1995, NIPS.

[3] Leemon C. Baird,et al. Residual Algorithms: Reinforcement Learning with Function Approximation , 1995, ICML.

[4] Andrew W. Moore,et al. Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[5] Sridhar Mahadevan,et al. Optimizing Production Manufacturing Using Reinforcement Learning , 1998, FLAIRS.

[6] Wilfried Brauer,et al. Multi-machine scheduling-a multi-agent learning approach , 1998, Proceedings International Conference on Multi Agent Systems (Cat. No.98EX160).

[7] Craig Boutilier,et al. Sequential Optimality and Coordination in Multiagent Systems , 1999, IJCAI.

[8] Andrew W. Moore,et al. Distributed Value Functions , 1999, ICML.

[9] Martin A. Riedmiller. Concepts and Facilities of a Neural Reinforcement Learning Control Architecture for Technical Process Control , 1999, Neural Computing & Applications.

[10] Martin A. Riedmiller,et al. A Neural Reinforcement Learning Approach to Learn Local Dispatching Policies in Production Scheduling , 1999, IJCAI.

[11] Michael Wooldridge,et al. Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence , 1999 .

[12] Martin Lauer,et al. An Algorithm for Distributed Reinforcement Learning in Cooperative Multi-Agent Systems , 2000, ICML.