FahzainAhmad/agent-hill-climb-supervised

This project implements a supervised deep learning system that learns to autonomously control a vehicle in the Countryside level of Hill Climb Racing. Using computer vision and a convolutional neural network (CNN), the model observes raw gameplay frames and predicts the correct driving action in real time — mimicking human input.

37
/ 100
Emerging

This project helps you create an AI agent that can autonomously play the mobile game Hill Climb Racing by observing the screen and mimicking human driving actions. It takes recorded gameplay video with corresponding driving inputs (accelerate, brake, or none) and produces a trained AI model capable of real-time control. This is ideal for researchers or enthusiasts interested in developing AI for game playing or behavioral cloning from visual data.

Use this if you want an AI to learn to play a simple racing game by watching recorded human gameplay and then autonomously control the vehicle in real-time.

Not ideal if you need an AI for competitive esports, complex strategy games, or scenarios requiring deep planning beyond immediate visual reactions.

game-AI behavioral-cloning computer-vision reinforcement-learning-lite game-automation
No License No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 5 / 25
Community 17 / 25

How are scores calculated?

Stars

73

Forks

13

Language

Python

License

Last pushed

Nov 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/FahzainAhmad/agent-hill-climb-supervised"

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