Yeah, I think this assumes an imperfect implementation. This relation can definitely be learned by the causal model (and is probably learned before the first real decision), but when the decision happen, it is cut. So it’s like a true LCDT agent learns about influences over agent, but forget its own ability to do that when deciding.
Yeah, I think this assumes an imperfect implementation. This relation can definitely be learned by the causal model (and is probably learned before the first real decision), but when the decision happen, it is cut. So it’s like a true LCDT agent learns about influences over agent, but forget its own ability to do that when deciding.