VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
Overview
This research presents VIGOR, a technique enabling model-based reinforcement learning agents to generalize zero-shot to unseen visual distractions such as changes in background, lighting, or camera settings.
Generated from attributed reports · Updated 2 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Artifact availability · code: reported pending
“e augmentation choice, drives robustness. A second instantiation on DreamerV3, a structurally distinct recurrent state-space model, also improves zero-shot generalization on both benchmarks, indicating backbone-agnostic benefits. Code and videos: https://vigor-gen.github.io/.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalVIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
This research presents VIGOR, a technique enabling model-based reinforcement learning agents to generalize zero-shot to unseen visual distractions such as changes in background, lighting, or camera settings.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).