Metraipolis › archive › dc_700d832ea5d0

Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation — arXiv:2608.05999

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05999
License (as archived)
CC0-1.0
Archived
2026-10-31T10:38:19.207Z
SHA-256 of the archived text
5f5033ed91e2e5ca9d8bc012800933009597d8a498ced08a36a5e1bfa64f4182
Stable URL of this page
https://metraipolis.com/documento/dc_700d832ea5d0

How to cite

Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation — arXiv:2608.05999 — arXiv (en), https://arxiv.org/abs/2608.05999 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_700d832ea5d0 (Metraipolis archive dc_700d832ea5d0, sha256 5f5033ed91e2e5ca9d8bc012800933009597d8a498ced08a36a5e1bfa64f4182)
BibTeX
@misc{dc700d832ea5d0,
  title = {Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation — arXiv:2608.05999},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05999},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_700d832ea5d0; sha256 5f5033ed91e2e5ca9d8bc012800933009597d8a498ced08a36a5e1bfa64f4182},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05999. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action (VLA) models have demonstrated remarkable capabilities in robotic manipulation by leveraging pretrained vision-language models. However, existing post-training methods predominantly optimize VLA models as flat policies, making it difficult to explicitly model task progression and perform robust long-horizon manipulation. Although hierarchical approaches introduce task decomposition, they mainly rely on supervised learning from offline demonstrations and cannot effectively improve execution through online interaction. To address this limitation, we propose Hierarchical Robotic Control (HiRoC), a hierarchical post-training framework that decouples high-level task planning from low-level action execution. The planner decomposes complex tasks into executable subgoals to provide explicit semantic guidance, while the executor continuously improves subgoal-conditioned action generation through reinforcement learning. To enable effective collaboration between the two modules, we further align the executor with planner-generated subgoals before reinforcement learning, mitigating the distribution misalignment between planning and execution. Extensive experiments across diverse robotic manipulation benchmarks demonstrate that HiRoC consistently outperforms strong baselines. Comprehensive analyses further validate the effectiveness of hierarchical post-training and the contribution of each key component.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.05999 — 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 2026-10-31T10:24:02.119Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).