I think the interesting feature of Solomonoff induction is that it does no worse than any other object from the same class (lower-semicomputable semimeasures), not just objects from a lower class (computable humans). I’m currently trying to solve a related problem where it’s easy to devise an agent that beats all humans, but difficult to devise one that’s optimal in its own class.
I think the interesting feature of Solomonoff induction is that it does no worse than any other object from the same class (lower-semicomputable semimeasures), not just objects from a lower class (computable humans). I’m currently trying to solve a related problem where it’s easy to devise an agent that beats all humans, but difficult to devise one that’s optimal in its own class.