- Second Amendment protesters defend gun rights with truly terrible signs 2 Years Ago
- David Lynch surprises fans by dropping Netflix short out of the blue 2 Years Ago
- Poop-focused parody of Kent State Gun Girl sparks conservative ire Today 11:58 AM
- 6-year-old raises $250K for Australian bushfires by making clay koalas Today 11:31 AM
- What you need to know about Clearview AI and its facial recognition app Today 10:36 AM
- Apple TV+ gets its first SAG Award while Netflix and Amazon nab 2 each Today 10:07 AM
- Facebook apologizes for translating Chinese president’s name to ‘Mr. Sh*thole’ Today 9:45 AM
- New York Times endorses Klobarren for president Today 8:45 AM
- 6 gift cards that make for the most thoughtful Valentine’s Day gift ideas Today 8:16 AM
- Studio Ghibli films are coming to Netflix—but not for Americans Today 8:13 AM
- Brad Pitt clutching Jennifer Aniston’s hand sparks all the rumors Today 7:47 AM
- The man who sold shares of himself on the internet Today 7:00 AM
- The rise of the conservative ‘mancast’ in a world of changing masculinity Today 6:00 AM
- Amazon’s ‘Troop Zero’ gives the underdog movie a stylized re-do Today 4:20 AM
- No, the first words of Trump’s tweets don’t match up to lyrics of ‘Break My Stride’ Sunday 10:28 PM
Machines may well be on the road to world domination, but one programmer decided that they should make a pit stop on the way: Mastering Mario Kart. YouTuber and programmer SethBling recently unveiled his newest creation, MariFlow, which uses machine learning to create a bot that can navigate Mario Kart courses like a human.
In a video titled, “How I trained a recurrent neural network called MariFlow to play Super Mario Kart like a human,” SethBling explains that MariFlow is a neural network (a type of artificial intelligence) that can learn by example. He trained the network to mimic his own gaming style by carefully examining 15 hours of gameplay to understand how he used the controller to drive. Ultimately, MariFlow’s goal is for the AI’s driving to be indistinguishable from a human.
So far, the network is winning! MariFlow drives on its own and wins gold medals in 50cc Mushroom and Flower Cups, but its creator admits that it has only managed to place second in Star Cup.
This is not the programmer’s first cool self-learning gaming project, either. In the same video, SethBling discusses another neural network, MarI/O, which learned how to master playing Mario World on its own. Unlike MariFlow, MarI/O’s game play evolved on its own. It produced small networks with evolved connections, which resulted in gameplay that could leave any human in the dust.
Want to help MariFlow learn how to play even better? SethBling released the MariFlow code and all of his recorded inputs so other players can help train it to whip around courses like a whiz.
Tiffanie Drayton is a geek culture and lifestyle reporter whose work covers everything from gender and race to anime and Xbox. Her work has appeared in Complex, Salon, Marie Claire, Playboy, and elsewhere.