AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is It Easier to Measure the Human Action Space?
In this paper, a, i believe it's called avoiding side effects by considering future asby victoria grikovna. The agent is comparing how much ability would have to achieve a wide variety of goals if it did some planned action compared to if it was already in this state and did nothing. In the paper, use this paing called te step wise in action base line. Once it's opened door, it's thinking, like, ok, if i did nothing, the vase would get broken. But because of this, like, step wise inaction base line, once it's open door, it’s thinking, Like, ok, if I did nothing