Conformal Policy Control
符合性策略控制
机构 * Johns Hopkins University(约翰霍普金斯大学) ; New York University(纽约大学)
AI总结 本文提出一种基于安全参考策略的符合性校准方法,用于在不违反安全约束的前提下,使优化但未测试的策略能够安全地进行探索,并在有限样本下提供理论保证。
Comments International Conference on Machine Learning (ICML), 2026. v4: Revised CPC theory to (a) show enforced smoothness for likelihood-ratio control parameter and (b) for general control parameter, assume smoothness only of constrained policy $π_t^{(β)}$ w.r.t. $β$ (rather than of $(l_i - α)\cdotπ_t^{(β)}$ or of conformal weights)