MASEM (NeurIPS '26): diverse state sampling for goal-conditioned robot RL
KyleMorgenstein · x · 2026-10-29
Roboticist Kyle Morgenstein highlights MASEM, a NeurIPS '26 work: finding feasible robot states for goal-conditioned RL is hard enough, but sampling maximally diverse states is another challenge. Diverse resets and goals help GCRL, yet contact and collision constraints make truly uniform sampling difficult — MASEM tackles this, another step toward solving dexterous manipulation in sim.
More from Embodied
- Dyna-2 trained on 1M+ hours of human video; data partner ships 450K hours monthly — Scobleizer · 2026-10-29
- Archon Robotics demos whole-body tactile intelligence: feeling inside a bag to grab items — micoolcho · 2026-10-29
- KUKA CEO on physical AI: how 600,000 deployed robots learn new tricks — lukas_m_ziegler · 2026-10-29
- Open-Source Stackchan Desk Robot Chats, Dances and Shows Memes — Full Build Guide Included — alexcovo_eth · 2026-10-29
- Robot steered by cloud AI: Dream Lab demos world-action model controlling MakerMods arms via public API — Scobleizer · 2026-10-29
- Sim-to-real for Piper-NIST robot arm: full pipeline and debug board shown — erwincoumans · 2026-10-29