Through Trial and Error to Collusion*
研究古诺寡头垄断中一种简单的试错学习过程：玩家在不知收益函数的情况下，仅根据利润增减调整产量，最终收敛到联合利润最大化的合谋结果。
In this article we study a very simple trial and error learning process in the context of a Cournot oligopoly. Without any knowledge of the payoff functions players increase, respectively decrease, their quantity as long as this leads to higher profits. We show that despite the absence of any coordination or punishing device this process converges to the joint‐profit‐maximizing outcome.