I Trained AI To “DOMINATE” Brackey’s Game

Nick ditched Sunday-night chill vibes to build a reinforcement-learning agent that absolutely crushes Brackey’s notoriously tough GoDot tutorial game. Inspired by a mining-optimization demo, he whipped up custom environments (14 versions so far!) and tossed the code in his GitHub repo—167 MB DMG files included if you’re game.

Massive shout-outs to Ed Beeching (GoDotRL guru) and Brackeys (legendary tutorial creator), plus a head’s-up that Nick’s off to present in Florida. Want the code, environments, or just to geek out? Hit him up on LinkedIn, Discord, Patreon, or any of the links in his post. Happy coding!

Watch on YouTube

Similar Posts

Loading similar posts...

Keyboard Shortcuts

Navigation
Next / previous item
j/k
Open post
oorEnter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help