Probably Approximately Correct Nash Equilibrium Learning

• Published in: arXiv.org
• Main Authors: Fele, Filiberto, Margellos, Kostas
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 24.04.2020
• Subjects: Computation; Computer Science - Computer Science and Game Theory; Computer Science - Systems and Control; Computer simulation; Economic models; Electric vehicle charging; Electric vehicles; Game theory; Mathematics - Optimization and Control; Multiagent systems; Optimization; Robustness (mathematics); Statistical analysis
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.1903.10387

We consider a multi-agent noncooperative game with agents' objective functions being affected by uncertainty. Following a data driven paradigm, we represent uncertainty by means of scenarios and seek a robust Nash equilibrium solution. We treat the Nash equilibrium computation problem within the realm of probably approximately correct (PAC) learning. Building upon recent developments in scenario-based optimization, we accompany the computed Nash equilibrium with a priori and a posteriori probabilistic robustness certificates, providing confidence that the computed equilibrium remains unaffected (in probabilistic terms) when a new uncertainty realization is encountered. For a wide class of games, we also show that the computation of the so called compression set - a key concept in scenario-based optimization - can be directly obtained as a byproduct of the proposed solution methodology. Finally, we illustrate how to overcome differentiability issues, arising due to the introduction of scenarios, and compute a Nash equilibrium solution in a decentralized manner. We demonstrate the efficacy of the proposed approach on an electric vehicle charging control problem.