Reinforcement Learning and Nonparametric Detection of Game-Theoretic Equilibrium Play in Social Networks
This work addresses the challenge of analyzing strategic interactions in social networks, offering tools for equilibrium learning and detection that are applicable to domains like energy markets and cybersecurity, though it appears incremental by building on existing game theory and signal processing concepts.
The paper tackles the problem of learning and detecting equilibrium behavior in non-cooperative games within social networks, presenting a reinforcement learning algorithm that converges to correlated equilibria and a non-parametric test for detecting equilibrium play in concave potential games, with applications demonstrated in energy markets and social network security.
This paper studies two important signal processing aspects of equilibrium behavior in non-cooperative games arising in social networks, namely, reinforcement learning and detection of equilibrium play. The first part of the paper presents a reinforcement learning (adaptive filtering) algorithm that facilitates learning an equilibrium by resorting to diffusion cooperation strategies in a social network. Agents form homophilic social groups, within which they exchange past experiences over an undirected graph. It is shown that, if all agents follow the proposed algorithm, their global behavior is attracted to the correlated equilibria set of the game. The second part of the paper provides a test to detect if the actions of agents are consistent with play from the equilibrium of a concave potential game. The theory of revealed preference from microeconomics is used to construct a non-parametric decision test and statistical test which only require the probe and associated actions of agents. A stochastic gradient algorithm is given to optimize the probe in real time to minimize the Type-II error probabilities of the detection test subject to specified Type-I error probability. We provide a real-world example using the energy market, and a numerical example to detect malicious agents in an online social network.