Diffusion Stochastic Learning Over Adaptive Competing Networks
This addresses the challenge of multi-agent competition in networked settings, such as in decentralized GAN training, but is incremental as it builds on existing diffusion learning methods.
The paper tackles the problem of stochastic dynamic games between competing teams of agents, proposing diffusion learning algorithms for zero-sum and non-zero-sum network games, with results showing stability performance validated through experiments on Cournot competition and decentralized GAN training.
This paper studies a stochastic dynamic game between two competing teams, each consisting of a network of collaborating agents. Unlike fully cooperative settings, where all agents share a common objective, each team in this game aims to minimize its own distinct objective. In the adversarial setting, their objectives could be conflicting as in zero-sum games. Throughout the competition, agents share strategic information within their own team while simultaneously inferring and adapting to the strategies of the opposing team. We propose diffusion learning algorithms to address two important classes of this network game: i) a zero-sum game characterized by weak cross-team subgraph interactions, and ii) a general non-zero-sum game exhibiting strong cross-team subgraph interactions. We analyze the stability performance of the proposed algorithms under reasonable assumptions and illustrate the theoretical results through experiments on Cournot team competition and decentralized GAN training.