English(EN) From Dueling Bandits to Episodic MDPs: Learning with Adversarial Preference Feedback

新框架解决了马尔可夫决策过程中的对抗性偏好反馈学习问题

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-26 04:00

研究人员开发了一个新的框架，用于在基于状态偏好的马尔可夫决策过程（MDP）中进行学习。该方法解决了选项比较不仅揭示偏好，而且影响后续状态的场景，例如在推荐系统中。该论文分析了该问题的最小最大遗憾，表明它受情节长度、状态数量和臂数量等因素的影响，并提出了实现最优遗憾率的算法。 AI

影响为顺序决策场景中的偏好反馈学习引入了新颖的理论框架。

排序理由该集群包含一篇学术论文，详细介绍了针对特定类型机器学习问题的新理论框架和算法。[lever_c_demoted from research: ic=1 ai=1.0]

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: 49 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了针对特定类型机器学习问题的新理论框架和算法。[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。

arXiv stat.ML TIER_1 English(EN) · Taira Tsuchiya, Shinji Ito, Haipeng Luo · 2026-10-26 04:00

从对偶土匪到情节马尔可夫决策过程：通过对抗性偏好反馈进行学习

arXiv:2507.11706v2 Announce Type: replace-cross Abstract: In dueling bandits, the learner compares two arms in each round and observes only which one is preferred. This paper asks what changes when the compared pair also affects the next state, as in a recommendation interface wh…