Skip to content Skip to footer
0 items - $0.00 0

Show HN: Beating Pokemon Red with RL and <10M Parameters by drubs

Show HN: Beating Pokemon Red with RL and

Show HN: Beating Pokemon Red with RL and <10M Parameters by drubs

15 Comments

  • Post Author
    jononor
    Posted March 5, 2025 at 6:26 pm

    Very nice! Nice to see demonstrations of reinforcement learning being used to solve non-trivial tasks.

  • Post Author
    xinpw8
    Posted March 5, 2025 at 6:28 pm

    This is a first-in-world, isn't it?

  • Post Author
    worble
    Posted March 5, 2025 at 6:39 pm

    Heads up, clicking "Next Page" just takes you to an empty screen, you have to use the navigation links on the left if you want to get read past the first screen.

  • Post Author
    bee_rider
    Posted March 5, 2025 at 6:52 pm

    Ah, very neat.

    Maybe some day the “rival” character in Pokemon can be played by a RL system, haha. That way you can have a “real player (simulated)” for your rival.

  • Post Author
    modeless
    Posted March 5, 2025 at 6:52 pm

    Can't Pokemon be beaten by almost random play?

  • Post Author
    bubblyworld
    Posted March 5, 2025 at 6:57 pm

    What an awesome project! I'm curious – I would have thought that rewarding unique coordinates would be enough to get the agent to (eventually) explore all areas, including the key ones. What did the agents end up doing before key areas got an extra reward?

    (and how on earth did you port Pokémon red to a RL environment? O.o)

  • Post Author
    rvz
    Posted March 5, 2025 at 7:20 pm

    Note: What makes this interesting is that this is a pre-LLM project which shows that in some projects you don't need an "LLM" for this. All you need is just a plain old reinforcement learning algorithm and a deep neural network which is perfect for this.

    This is what I want to see more of and goes against the hype of LLMs. What a great RL project.

    Meanwhile, "Claude" is still stuck somewhere in the game. Imagine the costs of running that vs this project.

  • Post Author
    mclau156
    Posted March 5, 2025 at 7:26 pm

    Could you have used the decompilations of pokemon on github? https://github.com/pret/pokered

  • Post Author
    levocardia
    Posted March 5, 2025 at 7:26 pm

    Really cool work. It seems like some critical areas (team rocket, safari zone) rely on encoding game knowledge into the reward function somehow, which "smuggles in" external intelligence about the game. A lot of these are related to planning, which makes me wonder whether you could "bolt on" an LLM to do things like steer the RL agent, dynamically choose what to reward, or even do some of the planning itself. Do you think there's any low-hanging fruit on this front?

  • Post Author
    differintegral
    Posted March 5, 2025 at 7:28 pm

    This is very cool, congrats!

    I wonder, does anyone have a sense of the approximate raw number of button presses required to beat the game? Mostly curious to see how that compares to the parameter count.

  • Post Author
    benopal64
    Posted March 5, 2025 at 7:47 pm

    Incredible work. I am just learning about PyBoy from your project, and it made me think of many fun ways to use that library to play Pokemon autonomously.

  • Post Author
    kerkeslager
    Posted March 5, 2025 at 9:17 pm

    Are there any uses for AI yet that aren't either:

    1. Doing things humans do for fun.
    2. Doing things that AI is horribly terrible at.

    ?

  • Post Author
    nimish
    Posted March 5, 2025 at 10:25 pm

    Considering how many things are less complicated than Pokemon, this is very cool

  • Post Author
    novia
    Posted March 5, 2025 at 11:01 pm

    Please stream the gameplay to twitch so people can compare.

  • Post Author
    endofreach
    Posted March 5, 2025 at 11:04 pm

    > Pokémon Red takes 25 hours on average for a new player to complete.

    Seriously? I've never really played video games, but i remember spending so much time on pokemon red when i was young. Not sure if i ever really finished more than once. But i'm pretty sure i must have played for more than 50h or so before even close to finish. My memory might trick me though.

    Not sure which pokemon version it was, but i got so hooked trying to get this "secret" pokemon which was just a bunch of pixels. Some kind of bug (of the game, not the type of pokemon). You had to do specific things in a park and other things and then surf up and down x-times on the right shore of an island… or something like that.
    I had no idea how it worked and got so hooked, i must have spent most of my playing time on things like that.

    Oh boy, memories…

Leave a comment

In the Shadows of Innovation”

© 2025 HackTech.info. All Rights Reserved.

Sign Up to Our Newsletter

Be the first to know the latest updates

Whoops, you're not connected to Mailchimp. You need to enter a valid Mailchimp API key.