Hacker News: stmonty

New comment by stmonty in "Teaching a World Model to Play Pokemon"

stmonty — Sat, 26 Sep 2026 02:41:36 +0000

I think seeing that thread on the front page gave me the courage to post my own post!

New comment by stmonty in "Teaching a World Model to Play Pokemon"

stmonty — Sat, 26 Sep 2026 02:40:41 +0000

I think it is possible but seems quite difficult to me from this experiment. The hard part is that Pokemon has a lot of different goals, and has many strategies to complete it. You would need a way to encode these intermediary goals in some way temporally that the model needs to learn to complete in order. For example, you need to collect all eight gym badges before you can challenge the Elite Four to win.

You could compose multiple network, one with the goal of learning how to interact with the world through the screenshots. This would probably require a lot of frames of the game from many diverse locations and scenarios--as the network would need to learn how battles works, items (though technically not strictly necessary), and general dialogue and menu interactions.

Then other networks could then try to learn to encode different intermediary goals trained on a bunch of noisy runs that complete that goal. Collecting this data seems tedious and difficult though and is a whole project in itself.

So my intuition is yes, but I don't think simply making my current model bigger would get us there. I see you have experience with world models--what would you try? ;)

New comment by stmonty in "Remembering Johannes Doerfert"

stmonty — Fri, 25 Sep 2026 23:13:51 +0000

Dying of cancer while that young is always a tragedy. I remember looking into some of the polyhedral compilation work in LLVM as I had never heard of it before. His contributions will live on.

New comment by stmonty in "Teaching a World Model to Play Pokemon"

stmonty — Fri, 25 Sep 2026 22:11:41 +0000

Author here, feel free to ask me any questions. Though I am no expert in this, just someone trying to learn and have some fun doing it.

Teaching a World Model to Play Pokemon

stmonty — Fri, 25 Sep 2026 21:02:48 +0000

Article URL: https://nostalgia.dev/posts/teaching-a-world-model-to-play-pokemon/

Comments URL: https://news.ycombinator.com/item?id=49849907

Points: 10

# Comments: 17

New comment by stmonty in "Ghostty 1.0"

stmonty — Thu, 26 Dec 2024 20:25:33 +0000

Awesome, I have been waiting for this since you originally announced it. I also enjoyed the blog posts.

New comment by stmonty in "Zb: An Early-Stage Build System"

stmonty — Thu, 19 Sep 2024 23:42:46 +0000

This looks awesome. I've had this same exact idea for a build system, but I haven't had the time to build it yet. Cool to see someone basically build what I had imagined!

New comment by stmonty in "Rabbit R1 It's a Scam"

stmonty — Wed, 05 Jun 2024 19:40:05 +0000

These two videos by the YouTuber CoffeeZilla seem relevant for exposing more about the R1 and its operation:

https://www.youtube.com/watch?v=NPOHf20slZg

https://www.youtube.com/watch?v=zLvFc_24vSM