DocumentCode :
3179729
Title :
Achieving pareto optimality through distributed learning
Author :
Marden, Jason R. ; Young, H. Peyton ; Pao, Lucy Y.
Author_Institution :
Dept. of Electr., Comput., & Energy Eng., Univ. of Colorado, Boulder, CO, USA
fYear :
2012
fDate :
10-13 Dec. 2012
Firstpage :
7419
Lastpage :
7424
Abstract :
We propose a simple payoff-based learning rule that is completely decentralized, and that leads to an efficient configuration of actions in any n-person game with generic payoffs. The algorithm requires no communication. Agents respond solely to changes in their own realized payoffs, which are affected by the actions of other agents in the system in ways that they do not necessarily understand. The method can be applied to the optimization of complex systems with many distributed components, such as the routing of information in networks and the design and control of wind farms.
Keywords :
Pareto optimisation; control system synthesis; game theory; large-scale systems; learning (artificial intelligence); complex system optimization; distributed components; distributed learning; information routing; n-person game; pareto optimality; payoff-based learning rule; wind farm control design; Benchmark testing; Games; Learning systems; Markov processes; Resistance; Turbines; Wind farms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Decision and Control (CDC), 2012 IEEE 51st Annual Conference on
Conference_Location :
Maui, HI
ISSN :
0743-1546
Print_ISBN :
978-1-4673-2065-8
Electronic_ISBN :
0743-1546
Type :
conf
DOI :
10.1109/CDC.2012.6426834
Filename :
6426834
Link To Document :
بازگشت