Policy Network
شبكة السياسة
شبكة عصبية تأخذ وضعية اللوح كمدخل وتُخرج توزيعاً احتمالياً على كل النقلات القانونية، تُستخدم لتوجيه البحث نحو النقلات الواعدة وتقليص عامل التفرّع.
A neural network that takes a board position as input and outputs a probability distribution over all legal moves, used to guide search toward promising moves and reduce the branching factor.
Also translated asشبكة اختيار النقلات، شبكة التوجيه الاستراتيجي
First appears in this corpus in: Mastering the Game of Go with Deep Neural Networks and Tree Search (2016)
Appears in these papers
- Mastering the Game of Go Without Human Knowledge2017in the sky ✦
- Mastering the Game of Go Without Human Knowledge2017in the sky ✦
- Mastering the Game of Go with Deep Neural Networks and Tree Search2016in the sky ✦
- MuZero: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model2020in the sky ✦
- MuZero: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model2020in the sky ✦
- QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation2018in the sky ✦