CS_ALearn/deep-rl-class
1
0
Fork 0
mirror of https://github.com/huggingface/deep-rl-class.git synced 2026-11-05 23:07:39 +08:00
Code Issues Projects Releases Wiki Activity

Update deep-q-network.mdx

Browse Source
This commit is contained in:
Antony Phillips
2023-06-18 12:20:58 +01:00
committed by GitHub
parent afb0e89b4a
commit 9c1e655b97
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
units/en/unit3/deep-q-network.mdx
View File

@@ -32,7 +32,7 @@ That’s why, to capture temporal information, we stack four frames together.
Then the stacked frames are processed by three convolutional layers. These layers **allow us to capture and exploit spatial relationships in images**. But also, because the frames are stacked together, **we can exploit some temporal properties across those frames**.
If you don't know what convolutional layers are, don't worry. You can check out [Lesson 4 of this free Deep Reinforcement Learning Course by Udacity](https://www.udacity.com/course/deep-learning-pytorch--ud188)
If you don't know what convolutional layers are, don't worry. You can check out [Lesson 4 of this free Deep Learning Course by Udacity](https://www.udacity.com/course/deep-learning-pytorch--ud188)
Finally, we have a couple of fully connected layers that output a Q-value for each possible action at that state.