Best part, "With this in mind I played more MarioKart to record new training data. I remember thinking to myself while trying to drive perfectly, “is this how parents feel when they’re driving with their children who are almost 16?”"
TensorKart: self-driving MarioKart with TensorFlow
21–30 of 70 posts
Re: TensorKart: self-driving MarioKart with TensorFlow
#22Next, have it upload its race results to kartlytics
omg! thanks for the refference to kartlytics. I had no idea this existed!
Re: TensorKart: self-driving MarioKart with TensorFlow
#23In contrast, here's what is effectively an oracle machine playing mario kart: https://www.youtube.com/watch?v=ZBNgbJ5hXtQ (Amazingly detailed) info: http://tasvideos.org/5243S.html
Thank you for sharing! I thought the Moo Moo Farm run was incredible on its own, THEN I saw the write-up. Blown away.
Re: TensorKart: self-driving MarioKart with TensorFlow
#24How are the original computer opponents able to play MarioKart?
Re: TensorKart: self-driving MarioKart with TensorFlow
#25This is pretty cool; as someone who is currently working on the second project (traffic sign recognition) for the Udacity "Self-Driving Car Engineer" nanodegree, using TensorFlow - it is interesting to me how it seems like the "standard" MNIST CNN can be adapted to so many other use cases.
For the project I am currently working on, I'm using a slightly modified form of LeNet - which isn't too different from the TF MNIST tutorial; after all, recognizing traffic signs isn't much different than recognizing hand-written numbers...
...but "driving" a course? That seems radically different to my less-than-expert-at-TensorFlow understanding, but that is only due to my ignorance.
I'm glad that these examples and demos are being investigated and made public for others - especially people learning like myself - to look at and learn from.
Re: TensorKart: self-driving MarioKart with TensorFlow
#26Personally I think the most impressive thing here isn't that you created a self-driving MarioKart, but that you trained TensorFlow based on input screenshots of your desktop.
I feel like that could be a good next step - a ubiquitous neural net model that, after mapping inputs, will learn to play any video game that's on your screen.
Re: TensorKart: self-driving MarioKart with TensorFlow
#27Quote: "Driving a new (untrained) section of the Royal Raceway:" So the author did a proper test of the model by scoring it on an unseen track to make sure it generalizes! This is very awesome!
How did we get from "bare minimum sensible testing" to "This is very awesome!"? Are things that bad on average?
Re: TensorKart: self-driving MarioKart with TensorFlow
#28How are the original computer opponents able to play MarioKart?
1. The AI in games has access to internal representations of game state and does not have to recognize it from pixels on screen. This is a massive difference.
2. The logic is usually a bunch of (human-authored) scripts consisting of if-else spaghetti.
Re: TensorKart: self-driving MarioKart with TensorFlow
#29great write up! this is awesome
Re: TensorKart: self-driving MarioKart with TensorFlow
#30Personally, I'm just a little impressed that you can train an active agent to play a game using old-fashioned supervised learning on screen states and controller states rather than relying on "action-oriented" learning techniques like reinforcement learning, online learning, or even a recurrent model.
It really shows how simple many control tasks actually are!