Learning Rationality in Potential Games

Stefan Clarke, Gabriele Dragotto, Jaime Fernández Fisac, Bartolomeo Stellato

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We propose a stochastic first-order algorithm to learn the rationality parameters of simultaneous and non-cooperative potential games, i.e., the parameters of the agents' optimization problems. Our technique combines an active-set step that enforces that the agents play at a Nash equilibrium and an implicit-differentiation step to update the estimates of the rationality parameters. We detail the convergence properties of our algorithm and perform numerical experiments on Cournot and congestion games. In practice, we show that our algorithm effectively finds high-quality solutions with minimal out-of-sample loss and scales to large datasets.

Original languageEnglish (US)
Title of host publication2023 62nd IEEE Conference on Decision and Control, CDC 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9798350301243
StatePublished - 2023
Event62nd IEEE Conference on Decision and Control, CDC 2023 - Singapore, Singapore
Duration: Dec 13 2023Dec 15 2023

Publication series

NameProceedings of the IEEE Conference on Decision and Control
ISSN (Print)0743-1546
ISSN (Electronic)2576-2370


Conference62nd IEEE Conference on Decision and Control, CDC 2023

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization


Dive into the research topics of 'Learning Rationality in Potential Games'. Together they form a unique fingerprint.

Cite this