Metraipolis › archive › dc_4745b99f8136
PACE: Phase-Progress-Aware Credit for Long-Horizon Embodied Manipulation — arXiv:2608.15026
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15026
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T23:03:28.539Z
- SHA-256 of the archived text
b8ac506dc1b2e19192a69a041ca634e49d882d97c9bca9ae8ae20ef31e8cc9a3- Stable URL of this page
https://metraipolis.com/documento/dc_4745b99f8136
How to cite
PACE: Phase-Progress-Aware Credit for Long-Horizon Embodied Manipulation — arXiv:2608.15026 — arXiv (en), https://arxiv.org/abs/2608.15026 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4745b99f8136 (Metraipolis archive dc_4745b99f8136, sha256 b8ac506dc1b2e19192a69a041ca634e49d882d97c9bca9ae8ae20ef31e8cc9a3)
BibTeX
@misc{dc4745b99f8136,
title = {PACE: Phase-Progress-Aware Credit for Long-Horizon Embodied Manipulation — arXiv:2608.15026},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15026},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4745b99f8136; sha256 b8ac506dc1b2e19192a69a041ca634e49d882d97c9bca9ae8ae20ef31e8cc9a3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15026. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Post-training of vision-language-action (VLA) models typically relies on expert demonstrations and policy interaction trajectories. However, in long-horizon manipulation, a single episode often spans hundreds of control steps and multiple phases, while success or failure is only revealed at episode termination. Policy improvement therefore requires step-level credit signals to distinguish behaviors that advance the task from those that stall or regress. We present PACE, a credit-assignment framework for post-training on long-horizon manipulation, centered on a phase-progress-aware critic. PACE consists of two key modules: (1) the Global-Local Cooperative Value-Correction Critic (GLC-Critic) aggregates visual and motion-difference features within local temporal windows to infer the phase and intra-phase progress of each step, and applies residual correction to a discretized remaining-cost distribution accordingly, enabling step-level credit assignment; (2) Progressive Policy Distillation (PPD) converts credit into positive and negative conditions via task-wise thresholds and trains a credit-conditioned action generation policy: it first protects the pretrained policy with high-credit positive samples, then incorporates all positive and negative credits to learn the quality boundary, and at inference amplifies high-credit behaviors through the difference between conditional outputs. Extensive simulation experiments and diverse real-world robotic-arm experiments demonstrate that PACE consistently achieves significant improvements over the strongest baseline. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-18 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.15026 — 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 2026-10-18T23:01:50.344Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).