In reinforcement learning, the output depends on the state of current input and the output of the next state depends on the out of the previous output.
Whereas in supervised learning, the decision made is based only on the current input. It uses labeled data sets to make decisions.
In reinforcement learning the output is dependent and hence they are labeled sequentially.
Whereas, in supervised learning, the outputs aren't dependent and hence it's not necessary to label them sequentially.