Optimization of non-stationary Stackelberg models using a self-adaptive evolutionary algorithm
Stackelberg’s game models involve an important family of Game Theory problems with direct application on economics scenarios. Their main goal is to find an optimal equilibrium between the decisions from two actors that are related one to each other hierarchically. In general, these models are complex to solve due to their hierarchical structure and intractability from an analytical viewpoint. Another reason for such a complexity comes from the presence of uncertainty, which often occurs because of the variability over time of market conditions, adversary strategies, among others aspects. Despite their importance, related literature reflects a few works addressing this kind of non-stationary optimization problems. So, in order to contribute to this research area, the present work proposes a self-adaptive meta-heuristic method for solving online Stackelberg’s games. Experiment results show a significant improvement over an existing method.
Stackelberg games, non-stationary bi-level optimization, differential evolution, self-adaptation, non parametric tests.
- There are currently no refbacks.