Q-function

الدالة Q

القيمة المتوقعة لدالة لوغاريتم الأرجحية للبيانات الكاملة، وهي الكمية التي تُعظِّمها خطوة التعظيم.

Q-function

Also translated asدالة التوقع

First appears in this corpus in: Maximum Likelihood from Incomplete Data via the EM Algorithm (1977)

Appears in these papers

Conservative Q-Learning for Offline Reinforcement Learning2020 in the sky ✦
Maximum Likelihood from Incomplete Data via the EM Algorithm1977 in the sky ✦
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor2018 in the sky ✦