Expert decision-makers (DMs) in high-stakes AI-assisted decision-making (AIaDM) settings receive and reconcile recommendations from AI systems before making their final decisions. We identify distinct properties of these settings which are key to developing AIaDM models that effectively benefit team performance. First, DMs incur reconciliation costs from exerting decision-making resources (e.g., time and effort) when reconciling AI recommendations that contradict their own judgment. Second, DMs in AIaDM settings exhibit algorithm discretion behavior (ADB), i.e., an idiosyncratic tendency to imperfectly accept or reject algorithmic recommendations for any given decision task. The human's reconciliation costs and imperfect discretion behavior introduce the need to develop AI systems which (1) provide recommendations selectively, (2) leverage the human partner's ADB to maximize the team's decision accuracy while regularizing for reconciliation costs, and (3) are inherently interpretable. We refer to the task of developing AI to advise humans in AIaDM settings as learning to advise and we address this task by first introducing the AI-assisted Team (AIaT)-Learning Framework. We instantiate our framework to develop TeamRules (TR): an algorithm that produces rule-based models and recommendations for AIaDM settings. TR is optimized to selectively advise a human and to trade-off reconciliation costs and team accuracy for a given environment by leveraging the human partner's ADB. Evaluations on synthetic and real-world benchmark datasets with a variety of simulated human accuracy and discretion behaviors show that TR robustly improves the team's objective across settings over interpretable, rule-based alternatives.

翻译：在高风险的人工智能辅助决策（AIaDM）环境中，专家决策者（DMs）在做出最终决策之前，会接收并协调来自人工智能系统的建议。我们识别出这些环境的关键特征，这些特征对于开发有效提升团队绩效的AIaDM模型至关重要。首先，决策者在协调与自身判断相矛盾的人工智能建议时，会因调动决策资源（如时间和精力）而产生协调成本。其次，AIaDM环境中的决策者表现出算法判别行为（ADB），即在特定决策任务中倾向于不完美地接受或拒绝算法建议的独特习惯。人类的协调成本和不完美的判别行为要求我们开发具备以下能力的人工智能系统：（1）有选择性地提供建议；（2）利用人类伙伴的ADB，在规范化协调成本的同时最大化团队的决策准确性；（3）具有内在的可解释性。我们将开发用于在AIaDM环境中为人类提供建议的人工智能系统这一任务称为“学习建议”，并首先引入人工智能辅助团队（AIaT）学习框架来解决该任务。我们实例化该框架以开发团队规则（TR）算法：该算法能够生成用于AIaDM环境的基于规则模型和建议。TR经过优化，能够有选择性地向人类提供建议，并通过利用人类伙伴的ADB，在给定环境中权衡协调成本与团队准确性。在包含各种模拟人类准确性和判别行为的合成与真实基准数据集上的评估表明，TR能够稳健地提升团队在不同环境中的目标表现，其效果优于可解释的、基于规则的替代方法。