Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

drubinstein.github.io

Post reply on HN
Print view View original

41–50 of 71 posts

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

#41

Post by endofreach »

> 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...

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

#42

Post by fancyswimtime »

xinpw8 wrote: post #14
VertanaNinjai wrote: post #11

Earlier quoted context omitted.

It can be brute forced if that’s what you mean. It has a fairly low difficulty curve and these old games have a grid system for movement and action selections. That’s why they’re pointing out the lower parameter amount and CPU. The point I took away is doing more with less.

It definitely cannot be beaten using random inputs. It doesn't even get out of Pallet Town after billions of steps. We tested...

the game has been beaten by fish

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

#43

Post by ludicity »

endofreach wrote: post #41

> 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 hoo…

It definitely took me way more than 25 hours as a kid to beat Pokemon Blue! But I was so young that I didn't understand that "Oak: Hello!" meant that someone called Oak was talking.

The glitched Pokemon you're talking about is Missingno by the way! I remember surfing up and down Cinnabar Island to do the same thing.

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

#44

Post by drubs »

wegfawefgawefg wrote: post #38
bubblyworld wrote: post #10

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)

you dont port it you wrap it. you can put anything in an rl environment. usually emulators are done with bizhawk, and some lua. worst case theres ffi or screen capture.

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

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

#45

Post by throwaway314155 »

Awesome! Why do you think the reward for reading signs helped? I'm assuming the model doesn't gain the ability to read and understand english just from RL, so what purpose does it serve other than to maybe waste ticks on signs that ultimately don't need to be read?

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

#47

Post by drubs »

throwaway314155 wrote: post #45

Awesome! Why do you think the reward for reading signs helped? I'm assuming the model doesn't gain the ability to read and understand english just from RL, so what purpose does it serve other than to maybe waste ticks on signs that ultimately don't need to be read?

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

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

#48

Post by Uehreka »

endofreach wrote: post #41

> 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 hoo…

There’s a guy on Youtube named JRose11 who is on a quest to beat Pokemon Red with all 151 of the original Pokemon individually. He’s about 100 Pokemon in at this point. He doesn’t use crazy speedrunning tactics (he wants to approximate a normal-ish playthrough) but because he knows exactly where to go, what to do and what’s skippable almost all of his runs are under 10 hours (many are under 6 and he did it with Mewtwo in just under 2).

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

#49

Post by xinpw8 »

benopal64 wrote: post #27

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.

Very good to hear. Join the pyboy/pokemon discords! https://discord.gg/UXpjQTgs https://discord.gg/EVS3tAGm

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

#50

Post by xinpw8 »

fancyswimtime wrote: post #42
xinpw8 wrote: post #14

Earlier quoted context omitted.

It definitely cannot be beaten using random inputs. It doesn't even get out of Pallet Town after billions of steps. We tested...

the game has been beaten by fish

dyor we only tested it with a pufferfish, courtesy of puffer.ai / pufferlib RL library. i promise it doesn't work with random inputs.
Post reply on HN