Metraipolis › archive › dc_a3eaddf8cb2c

Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning — arXiv:2610.10857

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10857
License (as archived)
CC0-1.0
Archived
2026-10-09T05:47:17.729Z
SHA-256 of the archived text
3f7c66b290769376ca2fa2c8b71cda34d51551dd6746a48455ca95c5350a47fb
Stable URL of this page
https://metraipolis.com/documento/dc_a3eaddf8cb2c

How to cite

Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning — arXiv:2610.10857 — arXiv (en), https://arxiv.org/abs/2610.10857 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a3eaddf8cb2c (Metraipolis archive dc_a3eaddf8cb2c, sha256 3f7c66b290769376ca2fa2c8b71cda34d51551dd6746a48455ca95c5350a47fb)
BibTeX
@misc{dca3eaddf8cb2c,
  title = {Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning — arXiv:2610.10857},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10857},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a3eaddf8cb2c; sha256 3f7c66b290769376ca2fa2c8b71cda34d51551dd6746a48455ca95c5350a47fb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10857. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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-term dependencies. However, recurrent models suffer from hidden-state collapse and gradient instability under backpropagation through time, while attention-based models are fundamentally limited by context length. To address these issues, we propose Keyframe Mnemonics, a novel self-supervised method that $\textit{discovers}$ a set of information-critical observations ($\textit{mnemonics}$) by learning an objective from randomly sampled past observations and using it as a reward for keyframe selection. We then train a BC policy that conditions on the discovered keyframes to model the action distribution. Under certain task-structure assumptions, our formulation provides context retention guarantees over an infinite horizon, while maintaining a small set of decision-relevant keyframes in the policy's working memory. We evaluate our method on synthetic memory domains, where mnemonic-conditioned BC policies achieve $100$% success rates (SR) and generalize to horizons orders of magnitude beyond training without performance degradation. Additionally, we evaluate on memory-intensive robot manipulation benchmark, achieving a $13.9$% average absolute SR improvement over the strongest baseline across $23$ tasks and retaining $80$% SR at $20\times$ longer horizons on a real robot. Code and videos are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.10857 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T05:47:00.499Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).