New results show us meaningful progress in how humans ought to be able to use robots, and the recipe is straightforward
I was looking for a survey of a similar topic, thanks! Are there any approaches where some RL is used in the loop to robustify the new task performance?
Not with ICL like this, but there are in general. That’s clearly the future for robot learning.
I was looking for a survey of a similar topic, thanks! Are there any approaches where some RL is used in the loop to robustify the new task performance?
Not with ICL like this, but there are in general. That’s clearly the future for robot learning.