Metraipolis › archive › dc_76f67dabbd6a
Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation — arXiv:2608.15680
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15680
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:04:12.603Z
- SHA-256 of the archived text
9562f39a37891760eb6df779031ad36e4615ee726f1f4bd33c00e762185a5d36- Stable URL of this page
https://metraipolis.com/documento/dc_76f67dabbd6a
How to cite
Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation — arXiv:2608.15680 — arXiv (en), https://arxiv.org/abs/2608.15680 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_76f67dabbd6a (Metraipolis archive dc_76f67dabbd6a, sha256 9562f39a37891760eb6df779031ad36e4615ee726f1f4bd33c00e762185a5d36)
BibTeX
@misc{dc76f67dabbd6a,
title = {Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation — arXiv:2608.15680},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15680},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_76f67dabbd6a; sha256 9562f39a37891760eb6df779031ad36e4615ee726f1f4bd33c00e762185a5d36},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15680. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-language-action (VLA) models improve robotic manipulation but remain vulnerable to compounding errors, scene changes, and off-trajectory states. Reinforcement learning can refine pretrained VLA policies, yet sparse success signals hinder exploration, while engineered dense rewards are costly and task-specific. Existing learned visual reward models often rely on static before-after observations, causing temporal ambiguity and weak discrimination between robustness-preserving variations and task-invalid failures under out-of-distribution (OOD) execution. We introduce Robo-Dopamine 2.0, a history- and OOD-aware process reward model with a pairwise prediction interface. It combines (1) history-conditioned pairwise rewards that use source-aligned reference panels for synthetic OOD queries and observed rollout history for online queries, while preserving the queried endpoints, and (2) an OOD-aware signed progress space that represents valid progress, robustness, failure, and recovery. A Signed-Hop Curriculum with transition-aware replay learns coarse execution ordering before fine-grained progress calibration. We also construct an OOD trajectory dataset and a five-family benchmark. Reference panels improve mean visual order consistency (VOC) from 0.967 to 0.986 and OOD-robust VOC from 0.906 to 0.958. With the same 400K pairwise-reward budget, Signed-Hop training with 25% replay reaches 0.9872 mean VOC, compared with 0.9858 for a matched-pool shuffled control. In downstream reinforcement learning, the full model achieves 86.8% mean RoboTwin success and 71/80 successful real-world insertions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.15680 — 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 2026-10-18T16:29:14.040Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).