kuds/rl-car-racing

Repository containing code and notebooks exploring how to solve Gymnasium's Car Racing through Reinforcement Learning

44
/ 100
Emerging

This project explores different reinforcement learning approaches to train an AI agent to drive a car in the Car Racing game environment. It takes in game observations (like screen images) and outputs optimal driving actions (steering, acceleration, braking) to achieve high scores. This is for AI researchers or students interested in comparing reinforcement learning algorithms on a classic control problem.

Use this if you are an AI researcher or student wanting to understand and compare the performance of various reinforcement learning algorithms (SAC, DQN, PPO) on a continuous control task like car racing.

Not ideal if you are looking for a plug-and-play solution for real-world autonomous driving or a high-performance gaming AI without understanding the underlying reinforcement learning principles.

reinforcement-learning AI-research game-AI continuous-control algorithm-comparison
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

10

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kuds/rl-car-racing"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.