# Why is Agnostic PAC learnability a stronger criterion as compared to the PAC learnability?

I am trying to understand the mentioned question. According to me, it should be other way around as it is easier to find hypothesis which is approximately correct compared to the optimal hypothesis in the hypothesis class (by agnostic PAC learnability).

• Look at the definitions. Does one of them imply the other? It would also help if you put the definition of agnostic PAC learnability here, as I cannot find a clear source for that. – Discrete lizard May 1 '19 at 8:11