Hacker News new | ask | show | jobs
by nottorp 17 days ago
There was good progress in training neural networks to play video games.

Unfortunately it doesn't seem to fit in some people's context because it was a few years ago.

Kind reminder: there is "AI" beyond LLMs.

2 comments

Several years ago I built a simple snake game and wrote a DQN from scratch to learn how to play it.

I was really proud of it at the time because I had to do a decent amount of reading and research since I wrote all of the NN code from scratch and wanted to add some more advanced algorithm optimisations which I hadn't done in previous projects.

I suspect a coding agent could spit the entire project out in 20 minutes now, but it was very cool at the time to build a game then watch my computer learn how to play it in real time.

OpenAI's Dota 2 adventures were super hype back in the days.
OpenAI Five doesn’t really know how to play games in general — it only knows how to play Dota.
The only game that matters.