Metraipolis › archive › dc_aed675f2f56b

Learning Robot Policies from Sparse Success Signals via STL-Guided Stein Variational Policy Gradient — arXiv:2609.31606

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31606
License (as archived)
CC0-1.0
Archived
2026-10-08T03:15:07.682Z
SHA-256 of the archived text
72337bb16e36432d5b38f4511bac75c4a4043b3fa2cdfe9960347fc8eb336c76
Stable URL of this page
https://metraipolis.com/documento/dc_aed675f2f56b

How to cite

Learning Robot Policies from Sparse Success Signals via STL-Guided Stein Variational Policy Gradient — arXiv:2609.31606 — arXiv (en), https://arxiv.org/abs/2609.31606 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aed675f2f56b (Metraipolis archive dc_aed675f2f56b, sha256 72337bb16e36432d5b38f4511bac75c4a4043b3fa2cdfe9960347fc8eb336c76)
BibTeX
@misc{dcaed675f2f56b,
  title = {Learning Robot Policies from Sparse Success Signals via STL-Guided Stein Variational Policy Gradient — arXiv:2609.31606},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31606},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aed675f2f56b; sha256 72337bb16e36432d5b38f4511bac75c4a4043b3fa2cdfe9960347fc8eb336c76},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31606. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning robot policies for tasks with sparse success signals is challenging when completion depends on coordinated actions, precise contact outcomes, or satisfying several conditions together. Intricate physical interactions with the world further complicate these requirements. Prior work using conventional reward shaping mechanisms provides dense feedback but local progress might not translate into eventual task completion. We present Signal Temporal Logic-guided Stein Variational Policy Gradient (STL-SVPG), a population-based method that uses smooth STL robustness as a trajectory-level training objective. Differentiating this objective through the dynamics assigns credit to policy actions according to their effect on the complete task specification, rather than local progress alone. We evaluate the approach on six quadcopter and manipulator tasks that involves event-triggered responses, strictly ordered behavior, responses within specified deadlines, and physical interaction with the world. STL-SVPG achieves the highest mean success rate among the compared methods on five of six benchmarks. Simulation-trained policies trained in simulation transfer temporal and contact task behavior to the real world.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.31606 — 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 2026-10-08T02:58:09.022Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).