论文标题
强大的算法勾结
Robust Algorithmic Collusion
论文作者
论文摘要
本文开发了一个正式框架，以评估经济游戏中学习算法的政策。我们调查了具有辅助定价政策的加强学习者是否可以成功地推断出从培训到市场的共谋行为。我们发现，在测试环境中，勾结会始终如一地分解。取而代之的是，我们观察到静态纳什戏。然后，我们表明限制算法的策略空间可以使算法串通稳健，因为它限制了竞争对手策略的过度限制。我们的发现表明，政策制定者应专注于旨在协调算法设计的公司行为，以使辅助政策稳健。
This paper develops a formal framework to assess policies of learning algorithms in economic games. We investigate whether reinforcement-learning agents with collusive pricing policies can successfully extrapolate collusive behavior from training to the market. We find that in testing environments collusion consistently breaks down. Instead, we observe static Nash play. We then show that restricting algorithms' strategy space can make algorithmic collusion robust, because it limits overfitting to rival strategies. Our findings suggest that policy-makers should focus on firm behavior aimed at coordinating algorithm design in order to make collusive policies robust.
