Eine Einladung zu Deep Reinforcement Learning (Foundations and Trends® in
70,72 €
These networks can be optimized with supervised learning if the target objective is differentiable. However, this is not the case for many interesting problems. Common objectives like intersection over union (IoU) and bilingual evaluation understudy (BLEU) scores or rewards cannot be optimized with supervised learning.
Jetzt bei Ebay:
