---
id: 20261011-T0-18
title: "Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning"
url: https://ai.daily.yangsir.net/daily/20261011-T0-18
issue_date: 2026-10-11
publish_date: 2026-10-10T04:00:00.000Z
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2610.10857
---

# Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning

arXiv:2610.10857v1 Announce Type: new Abstract: Behavior cloning (BC) in non-Markovian environments is a challenging problem because policies have to reason over contextual information over long horizons. Existing policy architectures rely on recurrent or attention-based mechanisms to capture long-t

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2610.10857)

**详情页**：https://ai.daily.yangsir.net/daily/20261011-T0-18

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*