DISCO distills tree search into policies, a CoRL 2026 Best Paper finalist for robot planning
yining_hong · x · 2026-11-04
DISCO: Distilled Tree Search over Continuous Actions was selected as a CoRL 2026 Best Paper Award finalist.
- Core idea: run Monte Carlo Tree Search in simulation, then iteratively distill its discoveries into a policy that executes directly at test time — no expensive search at deployment.
- Demonstrated strong performance on long-horizon object packing and stacking, including real-world transfer.
- Oral at CoRL on Nov 10, 11:00–11:30 AM at Hilton Austin; poster same day at JW Marriott Austin.
More from Embodied
- Ex-OpenAI robotics intern breaks down viral Astra robot-painting demo on Cerebras podcast — AccBalanced · 2026-11-04
- Embodied Agent Arena: Closed-Weight VLMs Lead All Five Robot Task Domains, Open-Weight Models Lag — Haojian Huang · 2026-11-04
- PrimeBot's PrimeSim: a generalist world model simulator trained on cross-embodiment demos — Travis Davies · 2026-11-04
- Physical AI Hackathon in SF Nov 7–8 features Dream-1 world action model and robot arms — Scobleizer · 2026-11-04
- Figure robot office demo looks like a sci-fi movie, says CEO Brett Adcock — adcock_brett · 2026-11-04
- 'Beyond Validation Loss': best pretraining checkpoint may hurt downstream RL fine-tuning — SongShuran · 2026-11-04