No-regret learning in harmonic games: Extrapolation in the face of conflicting interests - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2024

No-regret learning in harmonic games: Extrapolation in the face of conflicting interests

Résumé

The long-run behavior of multi-agent learning - and, in particular, no-regret learning - is relatively well-understood in potential games, where players have aligned interests. By contrast, in harmonic games - the strategic counterpart of potential games, where players have conflicting interests - very little is known outside the narrow subclass of 2-player zero-sum games with a fully-mixed equilibrium. Our paper seeks to partially fill this gap by focusing on the full class of (generalized) harmonic games and examining the convergence properties of follow-the-regularized-leader (FTRL), the most widely studied class of no-regret learning schemes. As a first result, we show that the continuous-time dynamics of FTRL are Poincaré recurrent, that is, they return arbitrarily close to their starting point infinitely often, and hence fail to converge. In discrete time, the standard, "vanilla" implementation of FTRL may lead to even worse outcomes, eventually trapping the players in a perpetual cycle of best-responses. However, if FTRL is augmented with a suitable extrapolation step - which includes as special cases the optimistic and mirror-prox variants of FTRL - we show that learning converges to a Nash equilibrium from any initial condition, and all players are guaranteed at most O(1) regret. These results provide an in-depth understanding of no-regret learning in harmonic games, nesting prior work on 2-player zero-sum games, and showing at a high level that harmonic games are the canonical complement of potential games, not only from a strategic, but also from a dynamic viewpoint.
Fichier principal
Vignette du fichier
Main.pdf (1.79 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04863624 , version 1 (04-01-2025)

Licence

Identifiants

Citer

Davide Legacci, Panayotis Mertikopoulos, Christos Papadimitriou, Georgios Piliouras, Bary S R Pradelski. No-regret learning in harmonic games: Extrapolation in the face of conflicting interests. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver, Canada. pp.1-36. ⟨hal-04863624⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More