🎴 Flashcard Mode
Reinforcement Learning for NLP
Card1 / 10
Mastered0
Review0
QuestionClick to flip
Which of the following is a common reinforcement learning algorithm used in NLP?
AnswerClick to flip back
A
Policy Gradients
💡 Explanation:
Policy Gradients are a class of reinforcement learning algorithms that directly optimize the policy function, rather than learning a value function.