You only have trouble if there is a goal-directed level beneath the lowest approval-directed level. The idea is to be approval-directed at the lowest levels where it makes sense (and below that you are using heuristics, algorithms, etc., in the same way that a goal-directed agent eventually bottoms out with useful heuristics or algorithms).
You only have trouble if there is a goal-directed level beneath the lowest approval-directed level. The idea is to be approval-directed at the lowest levels where it makes sense (and below that you are using heuristics, algorithms, etc., in the same way that a goal-directed agent eventually bottoms out with useful heuristics or algorithms).