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.
Show HN: Beating Pokemon Red with RL and <10M Parameters
21–30 of 71 posts
Re: Show HN: Beating Pokemon Red with RL and <10M Parameters
#22Really 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…
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 cut probably could have been handled by an LLM.
Re: Show HN: Beating Pokemon Red with RL and <10M Parameters
#23Can't Pokemon be beaten by almost random play?
It's impossible to beat with random actions or brute force, but you can get surprisingly far. It doesn't take too long to get halfway through route 1, but even with insane compute you'll never make it even to viridian forest.
Re: Show HN: Beating Pokemon Red with RL and <10M Parameters
#24Could you have used the decompilations of pokemon on github? https://github.com/pret/pokered
There's an entire section on how the decompilations were used :)
Re: Show HN: Beating Pokemon Red with RL and <10M Parameters
#25Could you have used the decompilations of pokemon on github? https://github.com/pret/pokered
if you helped with pret then god bless you
Re: Show HN: Beating Pokemon Red with RL and <10M Parameters
#26Note: 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…
Claude 3.7 recently failed to finish Pokemon after getting stuck in a corner and deciding it was impossible to get out
not our agents
a hierarchical approach would be superior. add rl to claude and it's gg
Re: Show HN: Beating Pokemon Red with RL and <10M Parameters
#27Incredible 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.
Re: Show HN: Beating Pokemon Red with RL and <10M Parameters
#28Could you have used the decompilations of pokemon on github? https://github.com/pret/pokered
There's an entire section on how the decompilations were used :)
Ok sorry I thought maybe there was a chance that the decomp project could edited in a way that would create a ROM that allowed RL to be done easier, but it seems like it just came in handy for looking up values along with the GB ASM tutorial, the alternative of my thought process is re-creating pokemon red in a modern language which you also mentioned
Re: Show HN: Beating Pokemon Red with RL and <10M Parameters
#29Really 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…
For well-known games like "Pokemon Red" I wonder how much of that game knowledge would be "smuggled in" by an LLM in it's training data if you just replaced the external info in the reward function with it/used it to make up for other deficiencies.
I think they allude to this in their conclusion, but it's less about the low-hanging fruit and more about designing a system to feedback game dialogue into the RL decision making process in a way that can be mutated as part of the RL(be it an LLM or something else)
Re: Show HN: Beating Pokemon Red with RL and <10M Parameters
#30This 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.
I imagine https://github.com/KeeyanGhoreshi/PokemonFireredSingleSequen... and https://www.youtube.com/watch?v=6gjsAA_5Agk. I believe this is something like 200k and is a slightly different game. Quite a bit less than 10m either way.