old_topic:action_space

차이

문서의 선택한 두 판 사이의 차이를 보여줍니다.

차이 보기로 링크

--- old_topic:action_space [2024/02/07 19:47] – 제거됨 - 바깥 편집 (Unknown date) 127.0.0.1
+++ old_topic:action_space [2024/03/23 02:42] (현재) – 바깥 편집 127.0.0.1
@@ 줄 1: / 줄 1: @@
+====== Action Space ======
+===== Large Action Space =====
+  * [[https://arxiv.org/pdf/2001.08116.pdf|Q-Learning in Enourmous Action Spaces via Amortized Approximate Maximization, 2020-01]]
+    * DeepMind, Volodymyr Mnih
+  * action space restriction
+    * masked softmax
+      * https://torchcraft.github.io/TorchCraftAI/docs/bptut-rl.html
+      * https://gist.github.com/kaniblu/94f3ede72d1651b087a561cf80b306ca
+      * https://discuss.pytorch.org/t/apply-mask-softmax/14212/12