RL Target Network

Creator

Created

2024 Apr 23 18:1

Editor

Edited

2024 Apr 23 18:2

Refs

Moving target을 방지하기 위해 Delayed updates

Compute targets with target network which don’t change in inner loop

y = r + \lambda Q_{\phi'}(s', argmax_{a'}Q_{\phi'} (s', a'))

////////