
Fully distributed Nash equilibrium seeking over timevarying communication networks with linear convergence rate
We design a distributed algorithm for learning Nash equilibria over time...
read it

A distributed proximalpoint algorithm for Nash equilibrium seeking under partialdecision information with geometric convergence
We consider the Nash equilibrium seeking problem for a group of noncoope...
read it

Gradient Play in nCluster Games with ZeroOrder Information
We study a distributed approach for seeking a Nash equilibrium in nclus...
read it

Fast generalized Nash equilibrium seeking under partialdecision information
We address the generalized Nash equilibrium (GNE) problem in a partiald...
read it

Distributed Nash Equilibrium Seeking under Quantization Communication
This paper investigates Nash equilibrium (NE) seeking problems for nonco...
read it

Reevaluating evaluation
Progress in machine learning is measured by careful evaluation on proble...
read it

Bestresponse dynamics in directed network games
We study public goods games played on networks with possibly nonrecipro...
read it
Nash equilibrium seeking under partialdecision information over directed communication networks
We consider the Nash equilibrium problem in a partialdecision information scenario. Specifically, each agent can only receive information from some neighbors via a communication network, while its cost function depends on the strategies of possibly all agents. In particular, while the existing methods assume undirected or balanced communication, in this paper we allow for nonbalanced, directed graphs. We propose a fullydistributed pseudogradient scheme, which is guaranteed to converge with linear rate to a Nash equilibrium, under strong monotonicity and Lipschitz continuity of the game mapping. Our algorithm requires global knowledge of the communication structure, namely of the PerronFrobenius eigenvector of the adjacency matrix and of a certain constant related to the graph connectivity. Therefore, we adapt the procedure to setups where the network is not known in advance, by computing the eigenvector online and by means of vanishing step sizes.
READ FULL TEXT
Comments
There are no comments yet.