Modeling Fake News in Social Networks with Deep Multi-Agent Reinforcement Learning

no code implementations • 25 Sep 2019 • Christoph Aymanns, Matthias Weber, Co-Pierre Georg, Jakob Foerster

We incorporate fake news into the model by adding an adversarial agent, the attacker, that either provides biased private signals to or takes over a subset of agents.

Multi-agent Reinforcement Learning Q-Learning +2

Fake News in Social Networks

no code implementations • 21 Aug 2017 • Christoph Aymanns, Jakob Foerster, Co-Pierre Georg

We model the spread of news as a social learning game on a network.