Adaptive Sampling + Pure RL Yields Robot Policies Beyond Prior Locomotion Limits

jeffclune · x · 2026-10-10

Jeff Clune shares a thread from researcher mateoguaman on adaptive sampling for robot RL.

• The author notes adaptive sampling/curricula helping RL has long been obvious: Hoeller and Rudin achieved groundbreaking locomotion results with adaptive curriculums, and the open-ended RL community (Clune and others) has explored this direction even longer.
• The work is a simple instantiation of that idea: no hand engineering, scales unusually well with compute, and produces policies solving robot tasks beyond what RL previously achieved.
• Behaviors are reactive, highly dynamic, and fast — learned entirely via RL, with no imitation data or motions to track.

Original post →

More from Embodied

• LeWAM: end-to-end JEPA world model plans 32x faster, lifts robot success to 89.7% — randall_balestr · 2026-10-10
• WorkOS gave 500 devs an ESP32-S3 conference badge; they put DOOM on it — DynamicWebPaige · 2026-10-10
• Hand-built robotic skin: AI asks to plug it into its head, reads touch in a minute — repligate · 2026-10-10
• Physical attention bias cuts cable-simulation prediction error by 15%+ — Avihai Giuili · 2026-10-10
• Wayve's AI Driver hits Turin roads in a Maserati Grecale just 4 weeks after integration — alexgkendall · 2026-10-10
• IROS 2026 Best Paper: humanoid robot learns tennis rallies from 5 hours of human motion data — qinzytech · 2026-10-10

Embodied channel →