kevinhughes27/TensorKart
self-driving MarioKart with TensorFlow
Implements end-to-end learning by capturing emulator screenshots and controller inputs during human gameplay, then training a convolutional neural network to predict joystick commands (steering, acceleration, button presses) from game frames. Uses `mupen64plus` emulation with `gym-mupen64plus` for automated agent evaluation, and demonstrates cross-track generalization—models trained on a handful of tracks can transfer to unseen courses with minimal data.
1,578 stars. No commits in the last 6 months.
Stars
1,578
Forks
253
Language
Python
License
MIT
Category
Last pushed
Dec 18, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kevinhughes27/TensorKart"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
idreesshaikh/Autonomous-Driving-in-Carla-using-Deep-Reinforcement-Learning
Deep Reinforcement Learning (PPO) in Autonomous Driving (Carla) [from scratch]
ArztSamuel/Applying_EANNs
A 2D Unity simulation in which cars learn to navigate themselves through different courses. The...
lexfridman/deeptraffic
DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.
KimangKhenng/Traffic-SImulation-and-Visualization
Traffic Intersection Simulation Using C++ and Qt
ikergarcia1996/Self-Driving-Car-in-Video-Games
A deep neural network that learns to drive in video games