็™ป้Œฒใ—ใฆๆ‹›ๅพ…ใƒชใƒณใ‚ฏใ‚’ๅ…ฑๆœ‰ใ™ใ‚‹ใจใ€ๅ‹•็”ปๅ†็”Ÿๅ ฑ้…ฌใจ็ดนไป‹ๅ ฑ้…ฌใ‚’็ฒๅพ—ใงใใพใ™ใ€‚

zeji yi
@ZejiYi
phd @CarnegieMellon | Intern at @Amazon FAR| Previously @Tsinghua_Uni | Studying Control & Robot Learning
ๅ‚ๅŠ  May 2024
380 ใƒ•ใ‚ฉใƒญใƒผไธญ    400 ใƒ•ใ‚กใƒณ
Common belief: Robot policies need continuous action heads; discrete actions are ๐ฅ๐ž๐ฌ๐ฌ ๐ง๐š๐ญ๐ข๐ฏ๐ž ๐š๐ง๐ ๐ฅ๐ž๐ฌ๐ฌ ๐ฉ๐ซ๐ž๐œ๐ข๐ฌ๐ž. โ—We find policies w/ the simplest discrete representations ๐ฆ๐š๐ญ๐œ๐ก ๐จ๐ซ ๐›๐ž๐š๐ญ continuous onesโ€”in sim & real, in single-step & diffusion/flow settings. Here's why ๐Ÿงต
ใ‚‚ใฃใจ่ฆ‹ใ‚‹