R3: Training Robots to Reason in Natural Language via RL
tw_killian · x · 2026-09-02
New work R3 trains robots to reason in natural language before acting using reinforcement learning. It argues that scaling test-time compute in robotics involves reasoning within the perception-action loop.
Related event: CMU's R³ Teaches Robots to Reason Before Acting via RL(3 posts)→
More from Embodied
- Opus-assisted open design: a $31k low-field head MRI sketched in hours — DreamFly_13 · 2026-10-18
- DIY robotics build: servo mechanism tested, wide yaw range but limited pitch — _Stocko_ · 2026-10-18
- Brain implants are restoring speech to people with ALS, Science reports — EricMTrautmann · 2026-10-18
- Meta wearables VP runs his AI agent across 3 phones and 23 pairs of glasses — nikola_mr64990 · 2026-10-18
- DeepSeek reportedly invests in embodied AI startups, in talks with robot founders — 量子位 · 2026-10-18
- AMI-EV: spinning prism gives event cameras stable texture, Science Robotics 2024 — RexDouglass · 2026-10-18