Metraipolis › archive › dc_b3e6c668dacc
Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement — arXiv:2609.17115
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.17115
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:30:34.801Z
- SHA-256 of the archived text
19d93eae88f7596778c5cadf63f7f2f361c70e5c8a2eae00da0cfea19c234228- Stable URL of this page
https://metraipolis.com/documento/dc_b3e6c668dacc
How to cite
Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement — arXiv:2609.17115 — arXiv (en), https://arxiv.org/abs/2609.17115 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b3e6c668dacc (Metraipolis archive dc_b3e6c668dacc, sha256 19d93eae88f7596778c5cadf63f7f2f361c70e5c8a2eae00da0cfea19c234228)
BibTeX
@misc{dcb3e6c668dacc,
title = {Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement — arXiv:2609.17115},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.17115},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b3e6c668dacc; sha256 19d93eae88f7596778c5cadf63f7f2f361c70e5c8a2eae00da0cfea19c234228},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17115. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-language-action (VLA) systems already bring together two valuable resources for robot learning: rich visual representations and demonstrations of successful task execution. Intrinsic Robot Rewarding (IRR) proposes to use these resources for a second, complementary purpose: evaluating the robot's own outcomes and providing feedback for policy improvement. Successful demonstration endpoints define task-specific references, and the policy's frozen visual encoder provides the feature space in which new outcomes are assessed. The core reward mechanism adds a reference bank and a scoring operation to the existing pipeline, without requiring a separate learned evaluator or an additional perception backbone. Our position is that this reuse offers a promising route to lower integration effort, efficient reward computation, and reduced recurring human outcome scoring. Building on established research in visual rewards and learning from experience, IRR brings these ideas into the robot's existing perception and demonstration pipeline. An operational COMAU Racer 3 demonstrator is available at technology readiness level 4 (TRL 4). This laboratory foundation supports the next research step: connecting internal outcome evaluation to physical policy improvement. We present the reward formulation, central research questions, and an evaluation methodology linking reward reliability to task success and supervision effort. The intended contribution is a reusable approach to learn and improve from the data and experience already available in industrial robot systems. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-16 in cs.RO). Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.17115 — 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 2026-10-15T21:30:17.349Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).