Fairness Incentives for Myopic Agents
Fairness Incentives for Myopic Agents
复制标题
对短视代理人的公平激励
DOI：
10.1145/3033274.3085154
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Zhiwei Steven Wu
中科院分区：
文献类型：
--
作者：
Sampath Kannan;Michael Kearns;Jamie Morgenstern;Mallesh M. Pai;Aaron Roth;R. Vohra;Zhiwei Steven Wu
我们考虑希望激励近视代理（例如Airbnb房东，可能会强调短期利润和财产安全）的设置，以公平对待到达客户，以防止对个人或团体的总体歧视。我们在经典和上下文的匪徒模型中对这种设置进行建模，其中近视药物根据当前的经验平均值最大化奖励，但也可以适合外源性支付，这可能会导致他们改变自己的选择。我们的公平概念要求，更合格的个人永远不会（概率）比较少的合格者更喜欢[8]。我们调查是否可以设计便宜的补贴或付款计划，以激励近视代理在所有或几乎所有一轮比赛中都公平地发挥作用。当校长具有有关近视剂状态的完整信息时，我们表明有可能在每回合中以总成本o（t）的补贴方案诱导公平竞争（对于带有k臂的经典设置，〜{o} （\ sqrtk3t），对于d维线性上下文设置〜{o}（d \ sqrtk3t））。如果本金的信息有更多的有限信息（外部监管机构或看门狗通常是这种情况），并且仅观察选择每个K组的成员的回合数量，但不观察到的回合数量，但不观察到由该回合的经验估计值近视剂，这种方案的设计变得更加复杂。我们通过上层和下边界在经典和线性的匪徒设置中表现出正面和负面的结果。
We consider settings in which we wish to incentivize myopic agents (such as Airbnb landlords, who may emphasize short-term profits and property safety) to treat arriving clients fairly, in order to prevent overall discrimination against individuals or groups. We model such settings in both classical and contextual bandit models in which the myopic agents maximize rewards according to current empirical averages, but are also amenable to exogenous payments that may cause them to alter their choices. Our notion of fairness asks that more qualified individuals are never (probabilistically) preferred over less qualifie ones [8]. We investigate whether it is possible to design inexpensive subsidy or payment schemes for a principal to motivate myopic agents to play fairly in all or almost all rounds. When the principal has full information about the state of the myopic agents, we show it is possible to induce fair play on every round with a subsidy scheme of total cost o(T) (for the classic setting with k arms, ~{O}(\sqrtk3T), and for the d-dimensional linear contextual setting ~{O}(d\sqrtk3T)). If the principal has much more limited information (as might often be the case for an external regulator or watchdog), and only observes the number of rounds in which members from each of the k groups were selected, but not the empirical estimates maintained by the myopic agent, the design of such a scheme becomes more complex. We show both positive and negative results in the classic and linear bandit settings by upper and lower bounding the cost of fair subsidy schemes.