註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Jagdeep Bhatia
@JagdeepBhatia8
Robotics PhD student @berkeley_ai advised by @svlevine Prev @MIT
加入 December 2021
397 正在關注    594 粉絲
How can generalist policies adapt to new challenges at deployment using skills they already have? We optimize VLA *prompt inputs* with reinforcement learning, enabling efficient real-robot adaptation on complex tasks where existing methods struggle. 🧵
顯示更多
0
3
87
20
轉發到社區