Credit Assignment
إسناد الائتمان
مشكلة تحديد أيّ القرارات أو الحالات السابقة تستحق الفضل (أو اللوم) في النتيجة النهائية. في الفارق الزمني، يتحكم المعامل λ في مدى توزيع هذا الائتمان زمنياً.
The problem of determining which past decisions or states deserve credit (or blame) for the final outcome. In temporal difference learning, the parameter λ controls how far back in time this credit is distributed.
Also translated asتوزيع المسؤولية التعلمية، تخصيص الفضل
First appears in this corpus in: A Learning Algorithm for Boltzmann Machines (1985)
Appears in these papers
- Backpropagation Through Time: What It Does and How to Do It1990in the sky ✦
- Backpropagation Through Time: What It Does and How to Do It1990in the sky ✦
- Learning Long-Term Dependencies with Gradient Descent is Difficult1994in the sky ✦
- A Learning Algorithm for Boltzmann Machines1985in the sky ✦
- A Learning Algorithm for Boltzmann Machines1985in the sky ✦
- Decision Transformer: Reinforcement Learning via Sequence Modeling2021in the sky ✦
- Decision Transformer: Reinforcement Learning via Sequence Modeling2021in the sky ✦
- Between MDPs and Semi-MDPs — A Framework for Temporal Abstraction in Reinforcement Learning1999in the sky ✦
- Temporal Difference Learning and TD-Gammon1995in the sky ✦
- Temporal Difference Learning and TD-Gammon1995in the sky ✦
- Learning to Predict by the Methods of Temporal Differences1988in the sky ✦