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.
Read on through a shared source
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.Why can’t a policy classify each move in isolation? →An action changes the next situation and thus the choices and rewards still available. The dependence is temporal even when the delay is short.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.
Compare the passages
there's no supervisor there's just this reward signalOnly the neural networks that produce the highest fitness are selected