Grid World Q-Learning ML Frameworks

Educational implementations of Q-learning and reinforcement learning algorithms applied to grid-based navigation environments. Includes projects demonstrating value iteration, SARSA, and related RL techniques in controlled simulations. Does NOT include general reinforcement learning frameworks, complex game AI, or non-grid-based environments.

There are 43 grid world q-learning frameworks tracked. 2 score above 50 (established tier). The highest-rated is Farama-Foundation/stable-retro at 58/100 with 354 stars.

Get all 43 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=grid-world-q-learning&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	Farama-Foundation/stable-retro Retro games for Reinforcement Learning Research	58	Established	354	C++
2	MatPoliquin/stable-retro-scripts Train models on retro games. AI vs AI contest. Pytorch C++ plugin for...	50	Established	39	C++
3	nadavbh12/Retro-Learning-Environment The Retro Learning Environment (RLE) -- a learning framework for AI	47	Emerging	186	C++
4	svpino/cs7641-assignment4 CS7641 - Machine Learning - Assignment 4 - Markov Decision Processes	41	Emerging	14	Java
5	Avalon-Benchmark/avalon A 3D video game environment and benchmark designed from scratch for...	40	Emerging	190	Jupyter Notebook
6	abhinavcreed13/ai-reinforcement-learning This project will implement value iteration and Q-learning. It will first...	35	Emerging	4	Python
7	F-a-b-r-i-z-i-o/maze-game Q-learning project where an agent learns by himself to find the exit inside...	30	Emerging	5	Python
8	PhilippOesch/QuickRLGym.js A small TypeScript/ JavaScript Framework for implementing, testing, and...	30	Emerging	2	TypeScript
9	LukaszMalucha/Pathfinder-AI Flask RESTful App with Q-learning AI algorithm	29	Experimental	9	Python
10	tristansokol/Bobcats Code used for the OpenAI Retro Contest for team Bobcats, spring 2018	29	Experimental	1	Jupyter Notebook
11	pcluteijn/MazeLearning Q-Learing algorithm solves simple mazes.	29	Experimental	7	MATLAB
12	vlfom/StepLearn Applying Markov Decision Processes and Q-Learning to a robot movement model	25	Experimental	4	Java
13	RodneyShag/GridWorldMDP Uses Markov decision processes (MDPs) and Temporal Difference (TD)...	24	Experimental	3	Java
14	htglvl/Final_prj Auto CS2 bot using reinforcement learning	23	Experimental	2	Jupyter Notebook
15	gaut2172/TreasureHuntGame AI pathfinding project using deep reinforcement learning. Deep Q-learning...	21	Experimental	7	Python
16	EricChen0104/ppo-icm-maze-exploration A curiosity-driven PPO + ICM reinforcement learning agent for autonomous...	21	Experimental	8	Python
17	thanhld94/Reinforcement-Learning Reinforcement Learning and Adaptive Resonance Theory	21	Experimental	1	Java
18	mbeps/custom-q-learning-agent Custom Reinforcement Learning agent built using Q-Learning. This is a...	20	Experimental	2	Python
19	LeoMartinezTAMUK/Markov_Decision_Process This project implements a Markov Decision Process (MDP) using Reinforcement...	19	Experimental	3	Python
20	ms-daniel/Reinforcement-Learning Program created in java with swing interface.	19	Experimental	3	Java
21	gtoubassi/SimpleReinforcementLearning A demonstration of table based, SARSA reinforcement learning for a simple...	18	Experimental	2	Java
22	tctibbs/matchbox-rl Matchbox-RL: A tangible reinforcement learning library for Python. Based on...	17	Experimental	—	Python
23	HarunaHaju/RL-STG Play STG with Reinforcement Learning	17	Experimental	1	Java
24	bzznrc/rl-toybox Tiny collection of minimal RL arcade-style games with shared training code	15	Experimental	2	Python
25	cabe9/NLBProject Reproducible NLB'21 mc_maze benchmark with lagged PCA latent regression and...	14	Experimental	—	Python
26	Styleflo/Gridword-DQN Gridword pour l'entraînement d'un DQN, afin de comprendre son fonctionnement	13	Experimental	—	Jupyter Notebook
27	MariaEduardaSampaio/TP3_Fundamentos-IA Reinforcement Learning project implementing Q-Learning and optimal policy...	13	Experimental	—	Jupyter Notebook
28	KriChau95/rl-cnn-maze-localization This project implements and compares strategies for self-localization within...	13	Experimental	—	Jupyter Notebook
29	yaacov/qlearner Q learning algorithm example in python	13	Experimental	—	Python
30	masoudslipknot/Reinforcment_Learning_ValueIteration Reinforcement- Learning project: Value Iteration Implementation.	12	Experimental	5	Java
31	Abdalkarim1979/Deep-Q-Learning-Maze-Explorer Educational Q-Learning maze with TensorFlow neural network and Pygame visualization.	12	Experimental	1	Python
32	PhuongLe/deep-q-learning-robot An implementation of Reinforcement Learning using the Q-Learning algorithm...	11	Experimental	4	Java
33	AlanDoesCS/Easy-Java-RL-Library A simple RL library, with a focus on DQNs	11	Experimental	—	Java
34	Ojaswy/Reinforcement-Learning Implementation of Reinforcement Learning	11	Experimental	—	Java
35	KaranAnchan/MDP_Optimal_Grid_Sim Explore the Gridworld Simulation 🌍🚀! An agent navigates a 5x5 grid to...	11	Experimental	—	Python
36	sababot/q-learning A Q-Learning implementation in C++, ready to be tweaked and modified to new projects	11	Experimental	3	C++
37	asaMavhungu/Maze-runner Pytorch-based FourRooms Environment with Epsilon-Greedy Policy	11	Experimental	—	Python
38	solar-san/AIDA-Project Final assignment for a university project, name of the course: Artificial...	11	Experimental	—	Jupyter Notebook
39	dizys/nyu-ai-lab-3 NYU Artificial Intelligence Course Lab 3: A generic Markov process solver.	11	Experimental	—	Python
40	Aatamte/gridworld-economy a gym-style API for training/evaluating agents in an economy	11	Experimental	—	Python
41	KaranAnchan/Windy_GridWorld_Sim 🌍💨 Explore the Windy Gridworld! An agent navigates a 10x7 grid facing wind...	11	Experimental	—	Python
42	itsamirrezah/MazeQLearning Implementation of Q-Learning Algorithm	11	Experimental	4	Java
43	manassarpatwar/QLearningJS An implementation of Q-Learning algorithm in JavaScript	10	Experimental	2	JavaScript