What cannot be recovered from the current observation?
Ask which distinctions the input representation discards. Earlier observations, feedback or prior knowledge may change what can be inferred.
Read on through a shared source
Did the game agent see too little or optimize the wrong thing? →A limited input can hide distinctions needed for a decision. A misleading objective can reward a bad move even when the state is visible.Where does the learning signal come from? →Finding patterns in unlabeled data and choosing actions from rewards both dispense with a teacher giving the right answer. Only the latter must account for the consequences of a decision.Reward and fitness both give feedback. What changes? →In reinforcement learning, rewards inform action choices. MarI/O uses a fitness score to select entire networks across generations.
Compare the passages
this has to have some mistakes since the representation is ambiguousthe future is independent of the past given the presentThe white squares stand for blocks the player can stand on