Interpolated stochastic interventions based on propensity scores, target policies and treatment-specific costs
基于倾向分数、目标政策和治疗特定成本的插值随机干预
AI总结 本文提出两种随机干预家族,连接因果建模与成本敏感决策,通过成本惩罚的信息投影生成闭式Boltzmann-Gibbs耦合,改进随机策略在有机法与参考法间平滑插值,提升稳健性与实用性。
Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 40(43):36654-36662, 2026