Sample Efficiency

كفاءة استخدام العيّنات

مقدار التعلّم الذي تستخرجه الخوارزمية من كمّ معيّن من بيانات التفاعل مع البيئة. الخوارزمية الأكفأ تتعلم أسرع من بيانات أقل.

How much learning an algorithm extracts from a given amount of environment interaction data. A more sample-efficient algorithm learns faster from less data.

Also translated asكفاءة البيانات، الاستثمار الأمثل للعيّنات

First appears in this corpus in: Between MDPs and Semi-MDPs — A Framework for Temporal Abstraction in Reinforcement Learning (1999)

Appears in these papers

Mastering Diverse Domains Through World Models2023 in the sky ✦
ELECTRA: Pre-Training Text Encoders as Discriminators Rather Than Generators2020 in the sky ✦
Hindsight Experience Replay2017 in the sky ✦
MuZero: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model2020 in the sky ✦
Between MDPs and Semi-MDPs — A Framework for Temporal Abstraction in Reinforcement Learning1999 in the sky ✦
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor2018 in the sky ✦
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor2018 in the sky ✦
Scaling Laws for Neural Language Models2020 in the sky ✦
End-to-End Training of Deep Visuomotor Policies2016 in the sky ✦