Epsilon-Greedy

ε-الجشع

استراتيجية اختيار أفعال تختار فعلاً عشوائياً باحتمال ε (استكشاف) وأفضل فعل معروف باحتمال 1−ε (استغلال)، مع تقليل ε تدريجياً أثناء التدريب للانتقال من الاستكشاف إلى الاستغلال.

An action selection strategy that picks a random action with probability ε (exploration) and the best known action with probability 1−ε (exploitation), gradually decreasing ε during training to shift from exploration to exploitation.

Also translated asإبسيلون الجشع، الاستكشاف بإبسيلون

First appears in this corpus in: Human-Level Control Through Deep Reinforcement Learning (2015)

Appears in these papers

Deep Reinforcement Learning with Double Q-Learning2016 in the sky ✦
Human-Level Control Through Deep Reinforcement Learning2015 in the sky ✦
Human-Level Control Through Deep Reinforcement Learning2015 in the sky ✦
Dueling Network Architectures for Deep Reinforcement Learning2016 in the sky ✦
Dueling Network Architectures for Deep Reinforcement Learning2016 in the sky ✦