AI Learns to DESTROY old CPUs | Mario Kart Wii
1,373,764
Published 2023-08-19
AI uses a variant of the Reinforcement Learning algorithm Rainbow DQN to learn how to play SNES Ghost Valley 2 against Mario Kart Wii's own CPUs
0:00 Intro
2:46 Training
4:54 A bit better
7:58 Final AI
If you are a C++ developer please help on this GitHub! Would allow me to get AI to play many other cool games.
github.com/Felk/dolphin/issues/41
Also thank you to my editor for editing this video!
@benji.botterill
www.benji-bott.com
Music:
1) 8-bit Sheriff - Wave Saver
2) A bit of power - Soara
3) Press X Twice - Lexica
4) Through the prism - Ava low
5) Backseat rider - Lupus Nocte
All Comments (21)
-
turns on items
-
Not having offroad on this track really seems to make it easier for the AI. cool stuff!
-
I love how aroused the reward function gets right before they cross the finish line on their final lap.
-
I appreciate how you do these on actual software and not just code your own software version of the game to simplify the task.
-
it's so crazy to see the AI even go for the lowtrick during the shortcut after 48-80 hours of training lol
-
I think it'd be pretty interesting to see it compete against the staff ghost of that track once it learns to use items such as mushrooms.
-
Conclusion: After 80 hours, AI becames Verstappen.
-
Have an AI and a human learn a game at the same time. Would be very interesting to see how the learning curves differ.
-
-
Imagine leaving it on for thousands of hours and learning how to do the Ultra Shortcut
-
It's fascinating to see how much AI has improved as a whole, not only in the game itself but in general. 5 years ago we wouldn't have been able to do this much with AI already. Also you're criminally underrated, keep it up!
-
i'm very happy this popped up in my recommendations; i'm on the spectrum and i've had pretty consistent mario kart hyperfixation periods since about 2017, and recently I've been very interested in the process of machine learning, so this video was basically a perfect match of two of my special interests. target audience reached! :)
-
For a bit of reference, sub 1 minute on this track is a decent time for a human in time trials, and a rather good time without powerups in vs mode, so a mid 1:06 is intriguing for sure, definitely showing some potential room for improvement but also demonstrating some clear progress to go with the gaps in it's methods.
-
The AI just collects and replicates gameplay from the average funky kong user
-
This is probably one of the more original ideas I've seen about MKWii, I have not seen any other video like this but this is great!
-
Having the AI receive greater rewards based on its speed seems to work great. It sounds like common sense, but every other attempts I've seen at training racing AI just sets checkpoints and rewards for crossing them, no variable to increase the reward if the time between checkpoints is lower or the speed higher.
-
I like how the reward skyrockets at the end of lap 3, as if it’s getting excited
-
I’m really curious how the AI was able to take input from the game. Was it using computer vision to actually process the whole screen in real time or was it integrated with the game engine in some way that let it get position data? I’m especially curious how it dealt with knowing where the other CPUs were and responding to bumps from them
-
You have no idea how long I’ve been waiting for something like this to happen!!
-
This is so cool! Great video
