Penalty-Regulated Dynamics and Robust Learning Procedures in Games

Abstract : Starting from a heuristic learning scheme for N-person games, we derive a new class of continuous-time learning dynamics consisting of a replicator-like drift adjusted by a penalty term that renders the boundary of the game's strategy space repelling. These penalty-regulated dynamics are equivalent to players keeping an exponentially discounted aggregate of their ongoing payoffs and then using a smooth best response to pick an action based on these performance scores. Owing to this inherent duality, the proposed dynamics satisfy a variant of the folk theorem of evolutionary game theory and they converge to (arbitrarily precise) approximations of Nash equilibria in potential games. Motivated by applications to traffic engineering, we exploit this duality further to design a discrete-time, payoff-based learning algorithm which retains these convergence properties and only requires players to observe their in-game payoffs: moreover, the algorithm remains robust in the presence of stochastic perturbations and observation errors, and it does not require any synchronization between players.
Document type :
Journal articles
Liste complète des métadonnées

Cited literature [43 references]  Display  Hide  Download

https://hal.inria.fr/hal-01235243
Contributor : Bruno Gaujal <>
Submitted on : Sunday, November 29, 2015 - 7:38:30 PM
Last modification on : Thursday, November 8, 2018 - 2:28:02 PM
Document(s) archivé(s) le : Saturday, April 29, 2017 - 2:14:02 AM

File

1303.2270v2.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Pierre Coucheney, Bruno Gaujal, Panayotis Mertikopoulos. Penalty-Regulated Dynamics and Robust Learning Procedures in Games. Mathematics of Operations Research, INFORMS, 2015, 40 (3), pp.611-633. ⟨10.1287/moor.2014.0687⟩. ⟨hal-01235243⟩

Share

Metrics

Record views

350

Files downloads

171