This is a much more nuanced take! At the beginning of Chapter 6, Jan proposes restricting our attention to agents which are limit computable.
Our agents are useless if they cannot be approximated in practice, i.e., by a regular Turing machine. Therefore we posit that any ideal for a ‘perfect agent’ needs to be limit computable (Δ02).
This seems like a very reasonable restriction! Any implementation needs to be computable, but it makes sense to look for theoretic ideals which can be approximated.
The levels of computability of various notions of optimal decision making are discussed in Jan Leike’s PhD thesis: https://jan.leike.name/publications/Nonparametric%20General%20Reinforcement%20Learning%20-%20Leike%202016.pdf
This is a much more nuanced take! At the beginning of Chapter 6, Jan proposes restricting our attention to agents which are limit computable.
This seems like a very reasonable restriction! Any implementation needs to be computable, but it makes sense to look for theoretic ideals which can be approximated.