Metraipolis › archive › dc_5067d276c142
VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning — arXiv:2610.02801
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02801
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:49:14.746Z
- SHA-256 of the archived text
6b0e3345b7f41246a3ff14074be86bd1273b5a9d6281ade508a71870cc008ee3- Stable URL of this page
https://metraipolis.com/documento/dc_5067d276c142
How to cite
VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning — arXiv:2610.02801 — arXiv, https://arxiv.org/abs/2610.02801 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5067d276c142 (Metraipolis archive dc_5067d276c142, sha256 6b0e3345b7f41246a3ff14074be86bd1273b5a9d6281ade508a71870cc008ee3)
BibTeX
@misc{dc5067d276c142,
title = {VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning — arXiv:2610.02801},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02801},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5067d276c142; sha256 6b0e3345b7f41246a3ff14074be86bd1273b5a9d6281ade508a71870cc008ee3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02801. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Model-based reinforcement learning (MBRL) achieves strong sample efficiency by planning within learned latent dynamics, yet its performance degrades substantially under unseen visual distractions such as background variations, lighting changes, or camera shifts. Unlike model-free RL, where encoder perturbations affect only single-step predictions, MBRL suffers from a two-level vulnerability: visual distractions first push encoder outputs out of distribution, and these errors then compound through recursive latent rollouts over the planning horizon. We propose visual generalization via latent-space consistency in model-based RL (VIGOR), a framework that enables zero-shot generalization to unseen visual distractions while retaining the sample efficiency of its MBRL backbone. VIGOR integrates three interdependent components: (i) asymmetric weak-to-strong augmentation, which pairs weak-only and weak-to-strong latent views within a single batch; (ii) dynamics-level consistency, which enforces augmentation-invariant transition predictions through direct latent regression; and (iii) encoder-level stabilization, which prevents encoder drift under the cross-augmentation supervision imposed by dynamics-level consistency. Evaluations on the DeepMind Control Suite (DMC) and Robosuite show that VIGOR outperforms state-of-the-art model-free and model-based baselines, surpassing the second-best baseline by 3.4% on DMC and 43.6% on Robosuite. Ablations further show that VIGOR's robustness is augmentation-agnostic: replacing the default augmentation with alternatives from distinct perturbation families preserves strong generalization, confirming that latent-space consistency, not the augmentation choice, drives robustness. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2610.02801 — 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 2026-10-05T22:45:55.632Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).