Re:Act-1: Transformer for Actions
by elcomet on Wednesday September 14, 2022 @05:26PM
(#32843612)
How many demonstrations were used ?
And was the feedback data used to train the model with reinforcement learning? Or did you request users to "correct" the action and get a supervised signal?
And was the feedback data used to train the model with reinforcement learning? Or did you request users to "correct" the action and get a supervised signal?