# kevinhughes27/TensorKart

self-driving MarioKart with TensorFlow

Repository: https://github.com/kevinhughes27/TensorKart
Canonical: https://ross.abutalabs.com/products/tensorkart
Language: Python
License: MIT
License Family: permissive
Topics: tensorflow, machine-learning
Last push: 2026-08-03T17:12:46+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 35, longevity 100
- inputs: {"age_days": 3535, "days_push": 30, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1575, forks 250 (observed 2026-08-28T04:05:05.896741+00:00)

## What it is
A demonstration project that trains a TensorFlow neural network to autonomously drive in Mario Kart 64 using the mupen64plus emulator. It records gameplay screenshots and joystick inputs, trains a CNN model, and plays the game through a gym-mupen64plus environment.

## Use cases
- train a neural network to play Mario Kart 64
- learn end-to-end self-driving with TensorFlow
- collect training data from emulator screenshots
- experiment with imitation learning from human gameplay
- set up a reinforcement learning baseline in a game environment

## When to choose
- you want a hands-on, end-to-end example of training a driving model from screen pixels
- you're learning TensorFlow, cuDNN, or gym environments with a fun project
- you want to experiment with imitation learning on a small dataset

## When to avoid
- you need a production-grade autonomous driving or RL framework
- you don't run Linux or can't set up mupen64plus with a joystick
- you need a maintained, well-supported library rather than a demo project

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, reinforcement-learning, simulation
- domain: machine-learning, deep-learning, computer-vision, gaming-tools, autonomous-vehicles
- platform: python
- tags: tensorflow, mario-kart-64, emulator, self-driving, imitation-learning, gym-environment, mupen64plus, demo-project, linux, gpu

## Member repositories
- kevinhughes27/TensorKart (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:05.896741+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:57:35.919706+00:00, confidence not recorded.
  - readme: https://github.com/kevinhughes27/TensorKart (fetched 2026-08-28T04:05:05.896741+00:00, sha f34c68605bb3)
- Data as of 2026-08-30T08:39:29.467469+00:00.