Robotics study: low-fidelity sim matches high-fidelity with little data; more failures can hurt rewards
mangahomanga · x · 2026-11-06
A technical thread on failure data and simulation fidelity in robot learning:
- Visual fidelity: Analysis across data scales shows that with little data, low-fidelity simulation matches high-fidelity simulation; as data grows, the higher-fidelity version holds up better.
- Failure data scaling: More failures do not always make better rewards. Scaling analysis shows adding failure data initially improves offline reward quality, then plateaus or hurts it. Cheap failure sources help up to a point, but beyond that they degrade reward modeling.
Related event: JHU Study Compares Four Failure Data Sources for Robot Reward Models(7 posts)→
More from Embodied
- Policy trained entirely in imagination matches PPO with 7.9× fewer simulator transitions — EpisodeYang · 2026-11-06
- Apple's mystery robot reportedly uses a Mac Mini as its planner brain — micoolcho · 2026-11-06
- Microdock v2 lets robot sit while docked, cutting servo power to zero — natesiggard · 2026-11-06
- Building an Asimov Robot in 22 Hours — and It Worked Out of the Box — whurley · 2026-11-06
- NEO-VLA drops the vision encoder: native VLA pretraining pays off on RoboTwin — liuziwei7 · 2026-11-06
- Gold Tesla Cybercab and Optimus shown at UP Summit — DMaguireARK · 2026-11-06