Feedback strategies control payoffs in complex multi-agent environments
Feedback autocratic strategies in stochastic games
Multiagent Systems
Summary
Managing outcomes when multiple decision-makers interact in changing environments can be very tricky. The authors studied special strategies that use current information to guide players’ rewards in these settings, called stochastic games. They show when and how these strategies can control rewards, extending ideas from simpler repeated games to more complicated situations. Their work helps connect game theory with control methods, and they tested it on examples involving social cooperation challenges.
What this means in practice
- •For traffic system planners: Implement feedback strategies to influence flow and payoffs in traffic models where agents respond dynamically.
- •For environmental policy designers: Design adaptive control policies that manage multiple stakeholders’ interactions towards sustainable resource use.
Tested on simulated data.
Authors
Masahiko Ueda
Abstract
A stochastic game is an optimal control problem for multiple agents in a stochastic environment. Stochastic games contain important practical problems, related to environmental issues or traffic flows. If the number of environmental states is one, such stochastic games are called repeated games. In repeated games, several strategies which unilaterally control payoffs have been proposed, and these strategies work in a mechanism similar to feedback control. In this paper, we generalize these strategies as feedback strategies in stochastic games, and investigate their properties. In particular, we provide a necessary and sufficient condition for such feedback strategies to work as controllers of payoffs under some assumptions. We demonstrate the performance of such feedback strategies in several examples related to social dilemmas. Our findings connect the theory of payoff control in repeated games to the theory of feedback control in stochastic games.