返回全部动态
噪声感知下智能体的风险感知决策策略研究
原标题：Risk-Aware Decision Policies for Agents Under Noisy Perception
AI 摘要
该研究提出了一种人工生命捕食者-猎物模型，用于模拟噪声感知下的觅食行为，并比较了多种考虑噪声预测的决策策略。实验表明，盲目信任感知标签会导致灾难性失败，而不确定性感知策略能显著提高生存率并减少致命错误。随着噪声增加，智能体行为从探索性转向保守性，凸显了不确定性感知决策的重要性。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
Computer Science > Machine Learning Title:Risk-Aware Decision Policies for Agents Under Noisy Perception View PDF HTML (experimental) Abstract:Perception in biological systems is inherently noisy, requiring organisms to make decisions under uncertainty where misclassification can be costly or fatal. We present an Artificial Life predator-prey model of foraging under noisy perception, and compare agent performance when using various policies that take into account their noisy predicti
发布时间：2026-08-10 12:00
抓取时间：2026-08-10 12:04
来源机构：arXiv