Online Parameter Identification of Cost Functions in Generalized Nash Games
- 15 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 71 (2) , 1350-1357
Abstract
This work studies the online parameter identification of cost functions in a generalized Nash game, where each player’s cost function is influenced by an observable signal and some unknown parameters. A learner can sequentially observe the equilibria reached by the game system as the observable signal changes, and its goal is to identify the unknown parameters in the cost functions. We recast this problem as an online optimization and introduce a novel online parameter identification algorithm. To be specific, we construct a regularized loss function that balances between conservativeness and correctiveness, where the conservativeness term ensures that the renewed estimates do not deviate significantly from the current estimates, while the correctiveness term is captured by the Karush–Kuhn–Tucker conditions of the generalized Nash equilibrium. For which, the balance is adjusted by a learning rate parameter. We then prove that when the players’ cost functions are linear with respect to the unknown parameters and the learning rate satisfies $\mu _{k} \propto 1/\sqrt{k}$, along with other assumptions, the regret bound of the proposed algorithm is $O(\sqrt{K})$ ($k$ and $K$ represent the current round of online algorithm and the total rounds of games played, respectively). Finally, we conduct numerical simulations on the parameter identification of a Nash–Cournot problem to demonstrate that the performance of our proposed online algorithm is comparable to that of the offline setting.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFA1004701)
- National Natural Science Foundation of China (72271187)
- National Natural Science Foundation of China (62173250)
- National Natural Science Foundation of China (62088101)
- Fundamental Research Funds for the Central Universities
- Shanghai Municipal Science and Technology Major Project (2021SHZDZX0100)
This publication has 28 references indexed in Scilit:
- An interaction-fair semi-decentralized trajectory planner for connected and autonomous vehiclesAutonomous Intelligent Systems, 2025
- Distributed Nash equilibrium seeking with order-reduced dynamics based on consensus exact penaltyControl Theory and Technology, 2023
- Using inverse optimization to learn cost functions in generalized Nash gamesComputers & Operations Research, 2022
- A dynamic pricing scheme for electric vehicle in photovoltaic charging station based on Stackelberg game considering user satisfactionComputers & Industrial Engineering, 2021
- A Generalized Nash–Cournot Model for the Northwestern European Natural Gas Markets with a Fuel Substitution Demand Function: The GaMMES ModelNetworks and Spatial Economics, 2012
- Revisiting Generalized Nash Games and Variational InequalitiesJournal of Optimization Theory and Applications, 2012
- On the variational equilibrium as a refinement of the generalized Nash equilibriumAutomatica, 2012
- Generalized Nash Equilibrium ProblemsAnnals of Operations Research, 2009
- Numerical Optimization1999
- Generalized Nash games and quasi-variational inequalitiesEuropean Journal of Operational Research, 1991