提出新算法iPI，高效判断智能体状态是否安全。
Algorithms for Deciding the Safety of States in Fully Observable Non-deterministic Problems: Technical Report
- 基于策略迭代设计新算法iPI，兼顾效率与可靠性。
- 理论证明其最坏情况为多项式时间，优于现有方法。
- 实测在复杂问题上显著优于传统算法，适合安全验证场景。
学习型动作策略在序列决策中越来越流行，但缺乏安全性保障。近期工作提出一个测试此类策略在初始状态和动作结果不确定性下的安全性的流水线。该流水线的核心是判断某状态是否安全（即从该状态存在安全策略），并找出导致状态不安全的“故障”（即从安全状态转移到不安全状态的状态-动作对）。他们最有效的算法TarjanSafe在基准测试中表现良好，但我们发现其最坏情况时间复杂度随状态空间呈指数增长。虽然存在线性时间替代方案，但在实际中速度较慢。本文提出新的策略迭代算法iPI，结合两者优势：在最佳情况下性能与TarjanSafe相当，同时保证多项式最坏时间复杂度。实验验证了理论分析，在适合TarjanSafe的问题上iPI性能相似；而在不适用的问题上，iPI扩展性显著优于前者。
原文摘要 · Abstract (English)
Learned action policies are increasingly popular in sequential decision-making, but suffer from a lack of safety guarantees. Recent work introduced a pipeline for testing the safety of such policies under initial-state and action-outcome non-determinism. At the pipeline's core, is the problem of deciding whether a state is safe (a safe policy exists from the state) and finding faults, which are state-action pairs that transition from a safe state to an unsafe one. Their most effective algorithm for deciding safety, TarjanSafe, is effective on their benchmarks, but we show that it has exponential worst-case runtime with respect to the state space. A linear-time alternative exists, but it is slower in practice. We close this gap with a new policy-iteration algorithm iPI, that combines the best of both: it matches TarjanSafe's best-case runtime while guaranteeing a polynomial worst-case. Experiments confirm our theory and show that in problems amenable to TarjanSafe iPI has similar performance, whereas in ill-suited problems iPI scales exponentially better.
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。