Suppose we have a game where there is no good measure of how "far" the target is (that we could use to nudge the agent towards the goal via the immediate returns).
If the agent gets only -1 reward per time step and experiencing a full episode where it reaches the goal is extremely improbable (it's equivalent to just blind search at this point), can it still learn?
If the agent gets no feedback whatsoever and has no information about the structure of the search space (just blind search, hoping to get lucky), then no, it can't learn. It has nothing to learn from. In your scenario, it has no information to enable it to improve: the feedback is always the same -- always an unending stream of -1,-1,-1,-1,-1,... unless it happens to get lucky. Without feedback, there's no basis for learning.
