Cheap Talking Algorithms

We simulate behaviour of independent reinforcement learning algorithms playing the Crawford and Sobel (1982) game of strategic information transmission. We show that a sender and a receiver training together converge to strategies approximating the ex-ante optimal equilibrium of the game. Communication occurs to the largest extent predicted by Nash equilibrium. The conclusion is robust to alternative specifications of the learning hyperparameters and of the game. We discuss implications for theories of equilibrium selection in information transmission games, for work on emerging communication among algorithms in computer science, and for the economics of collusions in markets populated by artificially intelligent agents.