为马尔可夫决策过程设计可解释的反事实策略，让决策更可控。
Counterfactual Strategies for Markov Decision Processes
- 将反事实推理转化为非线性优化问题，寻找最小策略修改
- 在四个真实数据集上验证，能有效降低不良结果概率
- 适合需要可解释性与安全性的复杂序列决策场景
反事实分析广泛用于解释模型输入的微小变化如何导致输出改变。然而，现有方法多聚焦单步决策，难以应用于序列决策任务。本文填补这一空白，提出适用于马尔可夫决策过程（MDP）的反事实策略。在MDP执行中，策略决定下一步执行哪个允许动作（具有已知概率效应）。给定一个导致不良结果概率超过阈值的初始策略，我们识别最小策略修改，使该概率降至阈值以下。我们将此类反事实策略编码为非线性优化问题的解，并进一步扩展以生成多样化的反事实策略。我们在四个真实世界数据集上评估该方法，证明其在复杂序列决策任务中的实际可行性。
原文摘要 · Abstract (English)
Counterfactuals are widely used in AI to explain how minimal changes to a model's input can lead to a different output. However, established methods for computing counterfactuals typically focus on one-step decision-making, and are not directly applicable to sequential decision-making tasks. This paper fills this gap by introducing counterfactual strategies for Markov Decision Processes (MDPs). During MDP execution, a strategy decides which of the enabled actions (with known probabilistic effects) to execute next. Given an initial strategy that reaches an undesired outcome with a probability above some limit, we identify minimal changes to the initial strategy to reduce that probability below the limit. We encode such counterfactual strategies as solutions to non-linear optimization problems, and further extend our encoding to synthesize diverse counterfactual strategies. We evaluate our approach on four real-world datasets and demonstrate its practical viability in sophisticated sequential decision-making tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。