vivek3141/pacman-ai

A.I. plays the original 1980 Pacman using Neuroevolution of Augmenting Topologies and Deep Q Learning

32
/ 100
Emerging

This project develops an AI that can play the classic 1980 Atari Pacman game, learning to navigate the maze, eat pellets, and avoid ghosts. It takes the game's visual state or internal data as input and outputs the optimal moves (up, down, left, right) for Pacman. This is designed for researchers or enthusiasts in artificial intelligence and machine learning who are exploring advanced game-playing algorithms.

No commits in the last 6 months.

Use this if you are an AI researcher or student interested in applying and comparing neuroevolution (NEAT) and deep reinforcement learning (DQN) techniques to a classic video game environment.

Not ideal if you are looking for a general-purpose Pacman game or a simple bot for casual play, as this project focuses on the underlying AI algorithms and their training.

artificial-intelligence-research reinforcement-learning game-ai neuroevolution deep-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

28

Forks

3

Language

Python

License

GPL-3.0

Last pushed

Apr 01, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vivek3141/pacman-ai"

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