Game Playing Agents ML Frameworks

AI agents trained using reinforcement learning and neuroevolution to autonomously play classic video games and simple game mechanics. Includes Deep Q-Learning, policy networks, and evolutionary algorithms applied to games like Flappy Bird, Pong, and Angry Birds. Does NOT include general game engines, web game frameworks, or non-learning-based game AI.

There are 46 game playing agents frameworks tracked. 1 score above 50 (established tier). The highest-rated is yenchenlin/DeepLearningFlappyBird at 51/100 with 6,792 stars.

Get all 46 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=game-playing-agents&limit=20"

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

#	Framework	Score	Tier	Stars	Language
1	yenchenlin/DeepLearningFlappyBird Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).	51	Established	6,792	Python
2	ChenglongChen/pytorch-DRL PyTorch implementations of various Deep Reinforcement Learning (DRL)...	49	Emerging	611	Python
3	nikp06/subwAI Scripts for training an AI to play the endless runner Subway Surfers using a...	46	Emerging	148	Python
4	vladfi1/phillip The SSBM "Phillip" AI.	46	Emerging	580	Python
5	kingyuluk/RL-FlappyBird Using reinforcement learning to train FlappyBird.	45	Emerging	82	Java
6	vita-epfl/social-nce [ICCV] Social NCE: Contrastive Learning of Socially-aware Motion Representations	44	Emerging	166	Python
7	Hamsath-Nejeeb/pong simple python pong game made by me:)	41	Emerging	1	Python
8	TomaszRewak/ML-games Machine learning games. Use combination of genetic algorithms and neural...	41	Emerging	285	JavaScript
9	sushantPatrikar/pingpongAI Ping Pong game, but AI plays it :robot:	39	Emerging	21	Python
10	vinaymancha/Subway-Surfers-AI Deep Convolutional Q learning based Self learning implementation for Subway...	37	Emerging	81	ASP
11	vkurenkov/haxball-chameleon Solving Haxball (www.haxball.com) using Imitation Learning methods.	37	Emerging	22	JavaScript
12	nelsonwenner/pingpong-AI :robot: Pingpong artificial intelligence.	36	Emerging	7	Python
13	leopnt/neft-godot Neuroevolution of Fixed Topology for Godot	36	Emerging	47	GDScript
14	xviniette/AsteroidsLearning Program that learns to avoid asteroids by machine learning (Neuroevolution)	35	Emerging	45	JavaScript
15	artem-oppermann/Deep-Reinforcement-Learning A collection of several Deep Reinforcement Learning techniques (Deep Q...	33	Emerging	37	Python
16	BY571/Deep-Reinforcement-Learning-Algorithm-Collection Collection of Deep Reinforcement Learning Algorithms implemented in PyTorch.	33	Emerging	80	Jupyter Notebook
17	trajectoryRL/trajectoryRL Bittensor Subnet 11 - Decentralized Reinforcement Learning for optimizing...	33	Emerging	7	Python
18	matamalaortiz/Pong-ML Machine Learning Pong Game in The Browser	32	Emerging	35	JavaScript
19	victorqribeiro/bangBangML Watch a Neural Network learns to shoot a target	31	Emerging	58	JavaScript
20	T3AS/ReMAV Implementation of "ReMAV: Reward Modeling of Autonomous Vehicles for Finding...	31	Emerging	4	Jupyter Notebook
21	Tillett/Game-Playing-with-Machine-Learning Game Playing with various AI and Machine Learning techniques	29	Experimental	19	Lua
22	TruongNV-hut/AIcandy_DQN_FlappyBird_xcrtkuqo Deep Q network to play flappy bird game	28	Experimental	48	Python
23	cpury/pong-rl Reinforcement Learning with Pong in the Browser via TensorFlow.js	27	Experimental	17	JavaScript
24	TailUFPB/space-invaders-tail Desenvolvimento do projeto da diretoria de Aprendizagem por Reforço, que...	25	Experimental	8	Jupyter Notebook
25	CreativeMindstorms/AI-LEGO-Pinball-Bot Python code that runs a full PinBall experience, with 3 different ways to...	24	Experimental	—	Python
26	rafaelcp/smbdataset Super Mario Bros. (NES) gameplay dataset for machine learning.	23	Experimental	13	Lua
27	toroleapinc/flappy-bird-ai DQN agent that plays flappy bird	21	Experimental	—	Python
28	guimnou/browser-marl-hideseek 🎮 Train NPCs using Proximal Policy Optimization in a browser-based 3D voxel...	21	Experimental	—	JavaScript
29	zhebrak/neuro_pong Atari Pong meets Neuroevolution	21	Experimental	7	JavaScript
30	BluemlJ/AiBirds The idea of this project is to write a deep reinforcement learning (DRL)...	20	Experimental	6	Python
31	ShihabYasin/Android-ColorPhun-Game-Agent-Using-Deeplearning A game agent to play autonomously a simple game idea namely ColorPhun.	18	Experimental	2	Java
32	Julio-Cezar-Candido/Projeto-Flappy-Bird Recriando o jogo "Flappy Bird", onde, uma inteligência artificial aprende a...	17	Experimental	1	Python
33	SrujanHR/smart-rockets-proxy-two This is the v2 of the dumb copy of Smart Rockets Genetic Algorithm...	17	Experimental	1	Python
34	Anuj-Deswal28/PROJECT---1 This is a Reinforcement-learning Flappybird game project, in which we train...	14	Experimental	—	Python
35	elhamabedi/function-approximation Air Combat Survival: Function Approximation Agent	13	Experimental	—	Python
36	alexxpz/EndFire Machine learning project to solve a strategic game.	13	Experimental	—	Jupyter Notebook
37	aashish-1904/doodle-jump-ai 🚀 Reinforcement Learning AI that masters Doodle Jump through advanced...	12	Experimental	4	Python
38	h24abdal/tic-tac-toe-reinforcement-learning Reinforcement learning solution for tic tac toe implemented in python.	11	Experimental	—	Jupyter Notebook
39	iamrishigandhi/pingpong it is the same game, ATARI made it in 1972, I did it in 2024.	11	Experimental	—	Python
40	CarsonBurke/WebGine A website game engine for creating my machine learning game projects	11	Experimental	—	JavaScript
41	WakateM/PongAI Intelligent AI agent that plays Pong	11	Experimental	—	C++
42	mattnix4/ping-pong-js Game Project Javascript	11	Experimental	—	JavaScript
43	Eshumkv/Kvasir-go A game coupled with a machine learning experience written in golang	11	Experimental	—	Go
44	kdrudy/flappyrl Flappy Bird Reinforcement Learning with RL4J	10	Experimental	2	Java
45	ajccom/machine-learning-rocket-car 基于神经网络进化的机器学习游戏例子	10	Experimental	2	JavaScript
46	suhhip/nn-js-pong Javascript based Pong game with "artificial intelligence" players, who are...	10	Experimental	2	JavaScript

Comparisons in this category

DeepLearningFlappyBird and RL-FlappyBird (51 vs 45) pingpongAI and pingpong-AI (39 vs 36)