SDPG accepted to CoRL 2026: end-to-end pixel-to-action robot policy training on a single RTX 4080 in hours
burny_tech · x · 2026-09-06
Researcher haoxiangyou announced that SDPG has been accepted to CoRL 2026. The algorithm makes end-to-end visual policy training accessible: it goes from pixels to actions on a single RTX 4080 within a few hours.
More from Embodied
- Wheelchair user gives Tesla Cybercab 10/10: seats match standard wheelchair height — EricETesla · 2026-09-06
- Wayve's AI-powered autonomous rides go live on Uber in London, running on NVIDIA DRIVE AGX — alexgkendall · 2026-09-06
- Model auto-optimizes ALOHA robot hardware design, validated on real hardware — SongShuran · 2026-09-06
- Transformer Transformer robot co-optimization paper accepted at CoRL 2026 — SongShuran · 2026-09-06
- GPT-6 Astra drives Onshape CAD in real time to build a robot from voice commands — dreamwieber · 2026-09-06
- Explicit gesture input failed AR/VR — AI contextual interpretation is the missing piece — mrjonfinger · 2026-09-06