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? ;)
VCFundedGenYer 6 hours ago [-]
Why is this a dupe of the other thread?
gchamonlive 6 hours ago [-]
This isn't, they are two independent projects making two independent models play Pokémon... independently
serious_angel 6 hours ago [-]
This is so dear sorrowful...
Art is a conversation between two people, that is a timeless communication between human.
An artwork to realize... to surf within to learn from, to listen to, to realize someone's images, someone's ideas, someone's worries, someone's messages... someone...
Art is someone's work of life, their experience, their... love...
There's human time in art... in a book, article, painting, soundscape, film, video-game... there's alive time of other human who reified their life experience, views, ideas... in an artwork and passed it to the outer world... to be inscribed in the infinitely magnificent history...
This...? This is just, sorry, deadly awful, dreadful, dark, and dear pain in heart... This is also disrespectful towards the Artists, Developers, people who worked on the Universe and this exact artwork...
This is utterly sorrowful...
gchamonlive 6 hours ago [-]
This is just a mathematical model playing a game from the 80s, it's not even trying to mimick artwork. How can you say it's not art to teach a dog how to play chess? Is it less of an art then to teach a machine to play Pokémon just because the machine isn't alive?
goolz 5 hours ago [-]
Small correction but it came out in Japan in 1996.
gchamonlive 5 hours ago [-]
Wopsie... I had it when I was a kid so late 90s and I remembered the Gameboy itself going way back in the 80s so one assumes
cheevly 3 hours ago [-]
Why are you on hackernews, jesus
conorcleary 9 hours ago [-]
Unfortunately, the developers of PGo! knowingly utilize the play of innocents' to train military SI.
Show HN: Jev Plays Pokémon Red - https://news.ycombinator.com/item?id=49845172
For reference, standard PPO has been able to beat the game end-to-end with a relatively small network https://drubinstein.github.io/pokerl/
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? ;)
Art is a conversation between two people, that is a timeless communication between human.
An artwork to realize... to surf within to learn from, to listen to, to realize someone's images, someone's ideas, someone's worries, someone's messages... someone...
Art is someone's work of life, their experience, their... love...
There's human time in art... in a book, article, painting, soundscape, film, video-game... there's alive time of other human who reified their life experience, views, ideas... in an artwork and passed it to the outer world... to be inscribed in the infinitely magnificent history...
This...? This is just, sorry, deadly awful, dreadful, dark, and dear pain in heart... This is also disrespectful towards the Artists, Developers, people who worked on the Universe and this exact artwork...
This is utterly sorrowful...