WEDGE turns navigation agents' own failures into targeted training worlds
mohitban47 · x · 2026-10-16
WEDGE is a policy-conditioned environment generation framework for navigation agents. The key observation: different agents fail under different environmental conditions on the same task, yet most environment generators ignore what each agent needs to practice. WEDGE analyzes an agent's failures to identify its weak spots, then generates new worlds that target those weaknesses while staying challenging-but-learnable.
Related event: WEDGE turns navigation agent failures into targeted training environments(4 posts)→
More from Embodied
- SHOES: 10 minutes of real-robot RL lets quadrupeds walk in shoes, CoRL 2026 paper — kscottz · 2026-10-16
- Tesla Cybercab robotaxis logged zero crashes in first two weeks of public rides, NHTSA data shows — elonmusk · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- WEDGE paper generates training environments conditioned on navigation agent failures — _akhaliq · 2026-10-16
- Viral meme nails AI's irony: it can write symphonies but can't do the dishes — briannekimmel · 2026-10-16
- Knödel Watch: animated vocabulary cards on ESP32-S3, open-sourced 4 days after unboxing — alexcovo_eth · 2026-10-16