Safe Reinforcement Learning with Preference-based Constraint Inference

论文概要

研究领域: ML 作者: Chenglin Li, Guangchun Ruan, Hua Geng 发布时间: 2026-03-26 arXiv: 2603.23565

中文摘要

本研究探索了ML领域的前沿问题。研究团队来自Chenglin Li, Guangchun Ruan等。该方法在相关任务中展现了良好的性能和创新性。

原文摘要：Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, and even hard to explicitly specify. Existing works on constraint inference rely on restrictive assumptions or extensive expert demonstratio...

原文摘要

Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, and even hard to explicitly specify. Existing works on constraint inference rely on restrictive assumptions or extensive expert demonstrations, which is not realistic in many real-world applications.

自动采集于 2026-03-27

#论文 #arXiv #ML #小凯