新研究：结构化因果老虎机扩展至部分因果图与反事实动作
Generalizing Causal Decision-Making: Markov Equivalence, Transportability and Counterfactuals
这篇论文把因果老虎机从“完全已知因果图”推进到部分已知也能用，能用别的环境数据和反事实实验来剪掉不值得试的动作。做 bandit、离线 RL 或因果决策的研究者可以直接参考它的图判据和 regret 保证。
arXiv 论文 2611.14066 将结构化因果老虎机（structural causal bandits）推广到三个此前未覆盖的场景：因果结构只有部分已知、奖励机制可从其他环境迁移、以及动作包含可实现的反事实操作。
技术层面，论文给出 Markov 等价类下最小干预集的图判据，并针对最大祖先图（maximal ancestral graph）刻画了可能最优的最小干预集；搜索算法可在偏祖先图（partial ancestral graph）表示的图类中找出至少在一张图内可能最优的干预集。作者还通过部分可迁移性（partial transportability）从源分布推导目标奖励边界，处理不可操纵变量，利用支配关系做动作剪枝，并在有效先验边界下给出 regret 保证。第三部分定义了反事实结构化因果老虎机，仅考虑由指定实验能力支持的动作，配套的最小性与可能最优性图刻画可在保留最优动作的前提下剔除等价或被支配的选择。
对做决策优化或离线强化学习的研究者，这套结果回答了一个实际问题：当因果知识不完整时，哪些干预值得花预算去探索。用指定结构化因果模型（SCM）的实验验证了剪枝与迁移边界对学习效率的影响。
Generalizing Causal Decision-Making: Markov Equivalence, Transportability and Counterfactuals
Structural causal bandits use causal knowledge to guide exploration when reward mechanisms are unknown. This paper extends the approach to partially known causal structure, information from other environments, and realizable counterfactual actions. First, we develop graphical criteria for minimal intervention sets under Markov equivalence and characterize possibly-optimal minimal intervention sets for maximal ancestral graphs. A search algorithm finds sets that are possibly optimal in at least one graph represented by a partial ancestral graph. Second, we derive target reward bounds from source distributions through partial transportability, accounting for non-manipulable variables. Dominance relations provide further bounds for action pruning and restricted exploration, with a regret guarantee under valid prior bounds. Third, we formulate counterfactual structural causal bandits over actions supported by specified experimental capabilities. Graphical characterizations of minimality and possible optimality yield algorithms that remove equivalent or dominated choices while preserving an optimal action. Experiments with specified structural causal models examine how these reductions and transferred bounds affect learning. Together, these results clarify how causal knowledge and experimental capabilities determine which actions merit exploration and guide learning within the retained action space.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include 因果推断, causal bandits, 反事实, 强化学习.
Source attribution: curated from arXiv cs.LG (@Min Woo Park, Sanghack Lee).