Live data from Hacker News

Viewing profile — drubs

drubs

HN member
Joined
Sun, Mar 02, 2025, 4:06 AM UTC
HN karma
77
Public activity
16 items

About drubs

Making models go brr

https://github.com/drubinstein https://x.com/dsrubinstein

Recent public activity

  1. comment
    Comment #46770814

    Fantastic work! This was a really fun collaboration.

  2. comment
    Comment #46446285

    Star the puffer https://github.com/PufferAI/PufferLib

  3. comment
    Comment #43303830

    Wouldn't make much sense. We generally train with 288 environments simultaneously. I've been thinking about ways to nicely stream all 288 environments though.

  4. comment
    Comment #43292027

    Really excited to be a part of the team!

  5. comment
    Comment #43280906

    Sounds cool to me.

  6. comment
  7. comment
    Comment #43274697

    It's silly, but signs were a way to incentivize the agent to explore deeper into the Safari Zone among other areas.

  8. comment
    Comment #43274265

    My first version of this project 5 years ago involved a python-lua named pipe using Bizhawk actually. No clue where that code went

  9. comment
    Comment #43273536

    There's a ton of applications for AI. Back when I was at Spotify, I co-authored Basic Pitch ( https://basicpitch.spotify.com/ ), an audio-to-midi library. There are a ton of uses f…

  10. comment
    Comment #43271156

    There's an entire section on how the decompilations were used :)

  11. comment
    Comment #43271136

    Wrote about this in the results section. I think there is a way to mix the two and simplify the rewards in the process. A lot of the magic behind getting the agent to teach and use…

  12. comment
    Comment #43270769

    The environments wouldn't concentrate enough in the Rocket Hideout beneath Celadon Game Corner. The agent would have the player wander the world reward hacking. With wild battles e…

  13. comment
    Comment #43270734

    and...fixed!

  14. comment
    Comment #43270507

    Thanks for the heads up. I just pushed a fix.

  15. comment
  16. story
    Show HN: Beating Pokemon Red with RL and <10M Parameters

    Hi everyone! After spending hundreds of hours, we're excited to finally share our progress in developing a reinforcement learning system to beat Pokémon Red. Our system successfull…