Trust Region
منطقة الثقة
منطقة محدّدة في فضاء المعاملات يُضمَن فيها أن النموذج التقريبي لدالة الهدف يبقى تمثيلاً موثوقاً للدالة الحقيقية، مما يمنع التحديثات المفرطة التي قد تُفسد السياسة.
A bounded region in parameter space where a local approximation to the objective is trusted to be accurate, preventing excessively large updates that could destabilize the policy.
Also translated asالمنطقة الآمنة، نطاق الثقة
First appears in this corpus in: Optimizing Neural Networks with Kronecker-Factored Approximate Curvature (2015)
Appears in these papers
- High-Dimensional Continuous Control Using Generalized Advantage Estimation2016in the sky ✦
- High-Dimensional Continuous Control Using Generalized Advantage Estimation2016in the sky ✦
- Optimizing Neural Networks with Kronecker-Factored Approximate Curvature2015in the sky ✦
- Proximal Policy Optimization Algorithms2017in the sky ✦
- Trust Region Policy Optimization2015in the sky ✦
- Trust Region Policy Optimization2015in the sky ✦