Achieving pareto optimality through distributed learning

Working paper

We propose a simple payoff-based learning rule that is completely decentralized, and that leads to an efficient configuaration of actions in any n-person finite strategic-form game with generic payoffs. The algorithm follows the theme of exploration versus exploitation and is hence stochastic in nature. We prove that if all agents adhere to this algorithm, then the agents will select the action profile that maximizes the sum of the agents' payoffs a high percentage of time. The algorithm r...

Expand abstract

Authors: Young, H; Marden, J; Pao, L

• Publication status: Published
• Publisher: University of Oxford Publisher's website
• Series: Department of Economics Discussion Paper Series
• Publication date: 2011-07-01
• Paper number: 557
• Keywords: distributed control; optimisation; learning