Cheap Talking Algorithms

• Tác giả: Daniele Condorelli, Massimiliano Furlan
• Ngôn ngữ: eng
• Ký hiệu phân loại: 511.4 Approximations formerly also 513.24 and expansions
• Thông tin xuất bản: 2023
• Bộ sưu tập: Báo, Tạp chí
• ID: 198324

Tóm tắt

We simulate behaviour of two independent reinforcement learning algorithms playing the Crawford and Sobel (1982) game of strategic information transmission. We adopt memoryless algorithms to capture learning in a static game where a large population interacts anonymously. We show that sender and receiver converge to Nash equilibrium play. The level of informativeness of the sender's cheap talk decreases as the bias increases and, at intermediate level of the bias, it matches the level predicted by the Pareto optimal equilibrium or by the second best one. Conclusions are robust to alternative specifications of the learning hyperparameters and of the game.