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.
Read on through a shared source
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.What if the best-scoring move is to pause the game? →Optimizing a score can reveal what its designer forgot to ask for.A better network or a longer look ahead? →Evolving a network changes its structure. Looking farther ahead changes how an agent evaluates future moves. Each addresses a different limitation.
Compare the passages
the representation is ambiguous and of course when it gets it wrongplaying Tetris well requires some thinking ahead, and this algorithm does not think very far ahead.