arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.00345econ.GNq-fin.EC
收藏

鲁棒性合谋

Robust Algorithmic Collusion

Nicolas Eschenbaum, Filip Mellgren, Philipp Zahn

摘要:

本文开发了一个正式的框架,以评估政策的学习算法在经济游戏。我们研究了具有合谋定价策略的学习代理是否可以成功地将合谋行为从训练中推断到市场。我们发现,在测试环境中的共谋一致打破。相反,我们观察静态纳什博弈。然后,我们表明,限制算法的策略空间可以使算法共谋鲁棒,因为它限制了竞争对手的策略过拟合。我们的研究结果表明,政策制定者应该专注于公司行为,旨在协调算法设计,以使合谋政策稳健。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑