English(EN) DT-JEPA: Learning to Predict Future Representations for Decision-Making

DT-JEPA框架学习可泛化的知识用于离线强化学习

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

研究人员推出了一种新颖的离线强化学习框架DT-JEPA，它结合了决策Transformer（DT）和联合嵌入预测架构（JEPA）。该方法旨在通过预测潜在空间中的未来表征来从无奖励轨迹中学习可泛化的知识，而不是仅仅依赖预期的未来回报。DT-JEPA捕获未来表征的条件分布，从而深入了解动力学的预测信息和不确定性。在D4RL基准上的实验表明，DT-JEPA能够高效地适应未见过的任务，并且优于现有的离线RL方法。 AI

影响该框架通过从无奖励数据中学习可泛化的知识，有望提高离线强化学习中对新任务的适应性。

排序理由该集群包含一篇详细介绍新机器学习框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 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: 9 / 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新机器学习框架的学术论文。[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, model release; 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Changxu Ni, Yiyang Ni, Jun Li, Feiran You, Hongyang Du, Haitao Zhao, Shi Jin · 2026-10-27 04:00

DT-JEPA：学习预测未来表征以用于决策

arXiv:2610.32657v1 Announce Type: new Abstract: Decision Transformer (DT) has demonstrated strong performance in various offline reinforcement learning (RL) tasks by conditioning action generation on expected future returns and historical trajectories. However, treating expected …

本文如何被排名

报道来源 [1]

DT-JEPA：学习预测未来表征以用于决策

相关实体

相关话题