I concede that VNM may be too high a bar, and I’ve seen some clever things done by relaxing the independence axiom. I don’t think I’ve seen any that change the basic problem of (acting as if there were) a single value function that the agent is optimizing. To be rational, there can be no separation of moral and non-moral domains.
I concede that VNM may be too high a bar, and I’ve seen some clever things done by relaxing the independence axiom. I don’t think I’ve seen any that change the basic problem of (acting as if there were) a single value function that the agent is optimizing. To be rational, there can be no separation of moral and non-moral domains.