English(EN) Prior-Data Fitted Networks for In-Context Off-Policy Evaluation

新的InCOPE方法用有限数据改进了策略外评估

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

研究人员开发了InCOPE，一种新颖的上下文策略外评估（OPE）方法，旨在利用有限的行为策略数据准确评估决策策略。该方法涉及在马尔可夫决策过程和策略对的生成先验上预训练一个网络，使其能够在没有特定任务更新的情况下预测新的表格问题的预期回报。在临床和其他表格环境中的实验证明了InCOPE在策略价值估计方面的有效性。 AI

影响增强了在真实数据有限的情况下评估AI决策策略的能力。

排序理由该集群包含一篇详细介绍特定机器学习任务新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 22 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍特定机器学习任务新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv stat.ML TIER_1 English(EN) · Shuguang Yu, Ting Li, Fan Zhou · 2026-10-27 04:00

用于上下文策略外评估的先验数据拟合网络

arXiv:2610.34035v1 Announce Type: new Abstract: Off-policy evaluation (OPE) is essential for assessing decision policies before deployment when online experimentation is costly or unsafe. Accurate estimation remains difficult when behavior-policy data are limited and the target p…

本文如何被排名

报道来源 [1]

用于上下文策略外评估的先验数据拟合网络

相关实体

相关话题