I think the thought experiments you give are pretty decisive in favour of the EDT answers over the CDT answers, and I guess I would agree that we have some kind of subtle control over the past, but I would also add:
Acting and conditioning on our actions doesn’t change what happened in the past; it only tells us more about it. Finding out that Ancient Egyptians were happier than you thought before doesn’t make it so that they were happier than you thought before; they already observed their own welfare, and you were just ignorant of it. While EDT would not recommend for the sake of the Ancient Egyptians to find out more about their welfare (the EV would be 0, since the ex ante distributions are the same) or even filter only for positive information about their welfare (you would need to adjust your beliefs for this bias), doesn’t it suggest that if you happen to find out that the Egyptians were better off than you thought, you did something good, and if you happen to find out that the Egyptians were worse off than you thought, you did something bad?
If we control the past in the way you suggest in your thought experiments, do we also control it just by reading the Wikipedia page on Ancient Egyptians? Or do we only use EDT to evaluate the expected value of actions beforehand and not their actual value after the fact, or at least not in this way?
And then, why does this seems absurd, but not the EDT answers to your thought experiments?
I think this is an interesting objection. E.g., “if you’re into EDT ex ante, shouldn’t you be into EDT ex post, and say that it was a ‘good action’ to learn about the Egyptians, because you learned that they were better off than you thought in expectation?” I think it depends, though, on how you are doing the ex post evaluation: and the objection doesn’t work if the ex post evaluation conditions on the information you learn.
That is, suppose that before you read Wikipedia, you were 50% on the Egyptians were at 0 welfare, and 50% they were at 10 welfare, so 5 in expectation, but reading is 0 EV. After reading, you find out that their welfare was 10. OK, should we count this action, in retrospect, as worth 5 welfare for the Egyptians? I’d say no, because the ex post evaluation should go: “Granted that the Egyptians were at 10 welfare, was it good to learn that they were at 10 welfare?”. And the answer is no: the learning was a 0-welfare change.
That is, suppose that before you read Wikipedia, you were 50% on the Egyptians were at 0 welfare, and 50% they were at 10 welfare, so 5 in expectation, but reading is 0 EV. After reading, you find out that their welfare was 10. OK, should we count this action, in retrospect, as worth 5 welfare for the Egyptians? I’d say no, because the ex post evaluation should go: “Granted that the Egyptians were at 10 welfare, was it good to learn that they were at 10 welfare?”. And the answer is no: the learning was a 0-welfare change.
This sounds like CDT, though, by conditioning on the past. If, for Newcomb’s problem, we condition on the past and so the contents of the boxes, we get that one-boxing was worse:
“Granted that the box that could have been empty was not empty, was it better to pick only that box?”. And the answer is no: you could have gotten more by two-boxing.
Of course, there’s something hidden here, which is that if the box that could have been empty was not empty, you could not have two-boxed (or with a weaker predictor, it’s unlikely that the box wasn’t empty and you would have two-boxed).
I think the thought experiments you give are pretty decisive in favour of the EDT answers over the CDT answers, and I guess I would agree that we have some kind of subtle control over the past, but I would also add:
Acting and conditioning on our actions doesn’t change what happened in the past; it only tells us more about it. Finding out that Ancient Egyptians were happier than you thought before doesn’t make it so that they were happier than you thought before; they already observed their own welfare, and you were just ignorant of it. While EDT would not recommend for the sake of the Ancient Egyptians to find out more about their welfare (the EV would be 0, since the ex ante distributions are the same) or even filter only for positive information about their welfare (you would need to adjust your beliefs for this bias), doesn’t it suggest that if you happen to find out that the Egyptians were better off than you thought, you did something good, and if you happen to find out that the Egyptians were worse off than you thought, you did something bad?
If we control the past in the way you suggest in your thought experiments, do we also control it just by reading the Wikipedia page on Ancient Egyptians? Or do we only use EDT to evaluate the expected value of actions beforehand and not their actual value after the fact, or at least not in this way?
And then, why does this seems absurd, but not the EDT answers to your thought experiments?
I think this is an interesting objection. E.g., “if you’re into EDT ex ante, shouldn’t you be into EDT ex post, and say that it was a ‘good action’ to learn about the Egyptians, because you learned that they were better off than you thought in expectation?” I think it depends, though, on how you are doing the ex post evaluation: and the objection doesn’t work if the ex post evaluation conditions on the information you learn.
That is, suppose that before you read Wikipedia, you were 50% on the Egyptians were at 0 welfare, and 50% they were at 10 welfare, so 5 in expectation, but reading is 0 EV. After reading, you find out that their welfare was 10. OK, should we count this action, in retrospect, as worth 5 welfare for the Egyptians? I’d say no, because the ex post evaluation should go: “Granted that the Egyptians were at 10 welfare, was it good to learn that they were at 10 welfare?”. And the answer is no: the learning was a 0-welfare change.
This sounds like CDT, though, by conditioning on the past. If, for Newcomb’s problem, we condition on the past and so the contents of the boxes, we get that one-boxing was worse:
Of course, there’s something hidden here, which is that if the box that could have been empty was not empty, you could not have two-boxed (or with a weaker predictor, it’s unlikely that the box wasn’t empty and you would have two-boxed).