ClaraChengGo
@ClaraChengGo
Babysitting robots with model-ready data at @openmind_agi @fabricFND
加入 June 2022
4.4K 正在關注 6.8K 粉絲
Even more solid looking back from today
This is what robotics policy training is heading to.
How it works now: engineer - reward function - mass training - success
But Nvidia ASPIRE is more like: Receive a new task - Execute the policy - Evaluate the outcome - Identify failure patterns - Optimize the policy - Repeat - Master the task
Self-improvement for robotics model.
顯示更多
