Cournot Competition and Endogenous Firm Size

We study the dynamics of firm size in a repeated Cournot game with unkown demand function. We model the firm as a type of artificial neural network. Each period it must learn to map environmental signals to both demand parameters and its rival's output choice. But this learning game is in the background, and we focus on the endogenous adjustment of network size. We investigate the long-run behavior of firm/network size as a function of profits, rival's size, and the type of adjustment rules used.