English(EN) PrefO2O: Zero-Shot Preference-Based Reinforcement Learning via Offline-to-Online Latent Preference Transfer

新框架实现零样本偏好驱动的强化学习

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

研究人员开发了PrefO2O，一种新颖的偏好驱动强化学习（PbRL）框架，可在新任务上实现零样本学习，无需额外的用户反馈。该方法从源任务的离线数据中学习任务不变的潜在偏好空间，从而将其偏好结构和奖励先验迁移到未见过的目标任务。PrefO2O利用置信度加权最优传输对齐来生成伪偏好监督，以进行在线奖励适应，在机器人操作和运动基准测试中表现出比现有偏好迁移基线显著的改进。 AI

影响该框架可以显著降低训练对齐AI代理的数据要求，从而加速机器人和其他领域的发展。

排序理由这是一篇详细介绍强化学习新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍强化学习新框架的研究论文。[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 cs.AI TIER_1 English(EN) · Ruiqi Wang, Dezhong Zhao, Xuesu Xiao, Erdem Biyik, Byung-Cheol Min, Guohua Chen · 2026-10-26 04:00

PrefO2O：通过离线到在线潜在偏好迁移实现零样本基于偏好的强化学习

arXiv:2610.31812v1 Announce Type: cross Abstract: Preference-based reinforcement learning (PbRL) has emerged as a promising paradigm for learning robot behaviors aligned with human intent. However, its scalability is fundamentally limited by the need to collect expensive human pr…

本文如何被排名

报道来源 [1]

PrefO2O：通过离线到在线潜在偏好迁移实现零样本基于偏好的强化学习

相关实体

相关话题