CS_ALearn/deep-rl-class
1
0
Fork 0
mirror of https://github.com/huggingface/deep-rl-class.git synced 2026-04-09 21:59:22 +08:00
Code Issues Projects Releases Wiki Activity

Merge pull request #316 from joeADSP/docs/unit-4-hands-on-action-space-description

Browse Source 
docs: update PixelCopter action space notes
This commit is contained in:
Thomas Simonini
2023-05-08 18:24:11 +02:00
committed by GitHub
parent add8c1c8b0 1105929bf8
commit e6daf3daa7
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
units/en/unit4/hands-on.mdx
View File

@@ -888,8 +888,8 @@ The observation space (7) 👀:
- next blocks bottom y location
The action space(2) 🎮:
- Up
- Down
- Up (press accelerator)
- Do nothing (don't press accelerator)
The reward function 💰:
- For each vertical block it passes, it gains a positive reward of +1. Each time a terminal state is reached it receives a negative reward of -1.