Yeah that was one of my first thoughts, but does it actually mean that informative inductive hypotheses can’t be conjectured more efficiently than guessing? I can imagine such an agent’s average efficacy across all problem types being fixed but still better than dart-throwing.
Yeah that was one of my first thoughts, but does it actually mean that informative inductive hypotheses can’t be conjectured more efficiently than guessing? I can imagine such an agent’s average efficacy across all problem types being fixed but still better than dart-throwing.