Corpus ID: 236447523

Gradient Play in $n$-Cluster Games with Zero-Order Information

  title={Gradient Play in \$n\$-Cluster Games with Zero-Order Information},
  author={Tatiana Tatarenko and Jan Zimmermann and J{\"u}rgen Adamy},
We study a distributed approach for seeking a Nash equilibrium in n-cluster games with strictly monotone mappings. Each player within each cluster has access to the current value of her own smooth local cost function estimated by a zero-order oracle at some query point. We assume the agents to be able to communicate with their neighbors in the same cluster over some undirected graph. The goal of the agents in the cluster is to minimize their collective cost. This cost depends, however, on… Expand

Figures and Tables from this paper


Gradient-Tracking over Directed Graphs for solving Leaderless Multi-Cluster Games
This work presents a distributed algorithm that converges with a linear rate to the optimal solution of the Nash Equilibria problem in agent-based multi-cluster games, where agents are separated into distinct clusters. Expand
On the linear convergence of distributed Nash equilibrium seeking for multi-cluster games under partial-decision information
A discrete-time distributed algorithm, called distributed gradient tracking algorithm (DGT), is devised based on the inter- and intra-communication of clusters, equipped with strategy variables including its own strategy and estimates of other clusters' strategies. Expand
Distributed convergence to Nash equilibria in two-network zero-sum games
This paper synthesizes a distributed saddle-point strategy and establishes its convergence to the Nash equilibrium for the class of strictly concave-convex differentiable functions with globally Lipschitz gradients. Expand
Learning Nash Equilibria in Monotone Games
This work proposes a distributed algorithm to learn a Nash equilibrium, whereby each agent uses only obtained values of her cost function at each joint played action, lacking any information of the functional form of hercost or other agents’ costs or strategy sets. Expand
Generalized Nash equilibrium seeking strategy for distributed nonsmooth multi-cluster game
To solve the GNE problem, a distributed nonsmooth algorithm is proposed using a projected differential inclusion and the convergence analysis of the proposed algorithm is established. Expand
Bandit learning in concave N-person games
This paper examines the long-run behavior of learning with bandit feedback in non-cooperative concave games and derives an upper bound for the convergence rate of the process that nearly matches the best attainable rate for single-agent bandit stochastic optimization. Expand
Nash equilibrium seeking for N-coalition noncooperative games
A seeking strategy is designed for the agents to find the Nash equilibrium of the N -coalition noncooperative game and it is based on an adaptation of a dynamic average consensus protocol and the gradient play. Expand
Constrained Consensus and Optimization in Multi-Agent Networks
A distributed "projected subgradient algorithm" which involves each agent performing a local averaging operation, taking a subgradient step to minimize its own objective function, and projecting on its constraint set, and it is shown that, with an appropriately selected stepsize rule, the agent estimates generated by this algorithm converge to the same optimal solution. Expand
An extremum seeking-based approach for Nash equilibrium seeking in N-cluster noncooperative games
The convergence results via Lyapunov stability analysis are established and the proposed seeking strategy performs as a unified strategy that solves the noncooperative games and the social cost minimization problems without utilizing explicit model information. Expand
Potential Games: A Framework for Vector Power Control Problems With Coupled Constraints
It is shown that many power control problems, with coupled constraints among the users, can be naturally formulated as potential games and, hence, efficiently solved. Expand