RL Environment Simulators ML Frameworks

Custom simulation environments and gym-compatible training frameworks for reinforcement learning across specific domains (trading, auctions, radio, accounting, games). Does NOT include RL algorithms, agents, or general-purpose game engines.

There are 52 rl environment simulators frameworks tracked. 3 score above 50 (established tier). The highest-rated is qgallouedec/panda-gym at 59/100 with 737 stars and 1,675 monthly downloads.

Get all 52 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=rl-environment-simulators&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	qgallouedec/panda-gym Set of robotic environments based on PyBullet physics engine and gymnasium.	59	Established	737	Python
2	nicrusso7/rex-gym OpenAI Gym environments for an open-source quadruped robot (SpotMicro)	54	Established	1,084	Python
3	amazon-science/auction-gym AuctionGym is a simulation environment that enables reproducible evaluation...	50	Established	187	Jupyter Notebook
4	upb-lea/openmodelica-microgrid-gym OpenModelica Microgrid Gym (OMG): An OpenAI Gym Environment for Microgrids	48	Emerging	219	Modelica
5	vietnh1009/Super-mario-bros-A3C-pytorch Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros	44	Emerging	1,108	Python
6	ntasfi/PyGame-Learning-Environment PyGame Learning Environment (PLE) -- Reinforcement Learning Environment in Python.	44	Emerging	1,057	Python
7	PySymGym/PySymGym Python infrastructure to train paths selectors for symbolic execution engines.	43	Emerging	13	Python
8	cove9988/TradingGym Trading Gym is an open source project for the development of reinforcement...	41	Emerging	222	Jupyter Notebook
9	jangirrishabh/toyCarIRL Implementation of Inverse Reinforcement Learning Algorithm on a toy car in a...	41	Emerging	178	Python
10	duburcqa/jiminy Jiminy: a fast and portable Python/C++ simulator of poly-articulated robots...	36	Emerging	285	Jupyter Notebook
11	dellalibera/gym-backgammon Backgammon OpenAI Gym	35	Emerging	54	Python
12	cassiusfive/balatro-gym Gymnasium Environment for Balatro	35	Emerging	36	Python
13	SciSharp/Gym.NET openai/gym's popular toolkit for developing and comparing reinforcement...	35	Emerging	140	C#
14	adipandas/gym_multirotor Multi-rotor Gym	35	Emerging	59	Python
15	google/balloon-learning-environment The Balloon Learning Environment - flying stratospheric balloons with deep...	34	Emerging	131	Python
16	NickKaparinos/OpenAI-Gym-Projects OpenAI Gym environment solutions using Deep Reinforcement Learning.	32	Emerging	80	Python
17	seoulai/gym Seoul AI Gym is a toolkit for developing AI algorithms.	32	Emerging	31	Python
18	harisankar95/voxelgym2D Gymnasium based RL environment for 2D grid path planning	31	Emerging	22	Python
19	ivy-llc/gym Fully differentiable RL environments, written in Ivy.	31	Emerging	66	Python
20	offworld-projects/offworld-gym OffWorld Gym: Open-Access Physical Robotics Environment for Real-World...	31	Emerging	57	Python
21	MartinThoma/banana-gym A simple stochastic OpenAI environment for training RL agents	31	Emerging	87	Python
22	JDatPNW/QPlane Fixed Wing Flight Simulation Environment for Reinforcement Learning	29	Experimental	80	Python
23	pathak22/exploration-by-disagreement [ICML 2019] TensorFlow Code for Self-Supervised Exploration via Disagreement	29	Experimental	129	Python
24	WUR-AI/PCSE-Gym CropGym is a highly configurable Python gymnasium environment to conduct...	29	Experimental	8	Jupyter Notebook
25	tamsri/radio-gyms Radio Gyms is an open-source bundle of AI environments for radio communications.	28	Experimental	13	Jupyter Notebook
26	futurely/openai-universe-agents Deep reinforcement learning agents for OpenAI universe environments	26	Experimental	7	Python
27	lab-v2/pyreason-gym An OpenAI wrapper for PyReason to use in a Grid World reinforcement learning setting	25	Experimental	32	Python
28	Yusei406/calvano-qlearning Q-learning oligopoly simulation (Calvano et al., 2020) — high-fidelity...	25	Experimental	2	Python
29	rickstaa/stable-gym This package contains several gymnasium environments with positive definite...	25	Experimental	12	Python
30	purvasingh96/gym-fraud 💳 Creates a new gym environment for credit-card anomaly detection using Deep...	24	Experimental	19	Jupyter Notebook
31	dimgold/Artificial_Curiosity Adaptive Reinforcement Learning of curious AI basketball agents	23	Experimental	22	Jupyter Notebook
32	lil-lab/knotgym [NeurIPS DB 2025] A gym environment for visual spatial reasoning - knot so simple :)	23	Experimental	15	Python
33	Div-Infinity/XQL Extreme Q-Learning: Max Entropy RL without Entropy	23	Experimental	87	Python
34	ThalesGroup/open-the-chests Open-the-chests is a training environment for event-patterns recognition.	23	Experimental	6	Python
35	MGokcayK/DynaG Dynamic System solver for reinforcement learning environment. It solves ODE...	22	Experimental	1	C++
36	doctorcorral/gyx Reinforcement Learning environment for Elixir	22	Experimental	34	Elixir
37	felipelodur/Q-Learning-Taxi-v2 Implementation of Q-Learning to learn optimal q-table of "Taxi-v2 Open AI...	22	Experimental	5	Jupyter Notebook
38	AlessandroPomponio/atari-bowling-ppo An autonomous agent that learns to play Atari Bowling using Reinforcement...	22	Experimental	7	Jupyter Notebook
39	ethicsai/ethical-smart-grid Reinforcement learning environment for learning ethical behaviours in a...	21	Experimental	3	Python
40	Sujyeet/SPEED-Intelligent-Racing-Agents Comparative research platform for Deep Reinforcement Learning and heuristic...	18	Experimental	4	C#
41	abbas-rz/ImitationReplay A focused toolkit for capturing human demonstrations in Gym/Gymnasium...	16	Experimental	1	Jupyter Notebook
42	Thableaddles57/reinforcement-learning-gym Implementations of various reinforcement learning algorithms (e.g.,...	14	Experimental	—	Python
43	markusdumke/q_sigma_lambda Reinforcement Learning: Implementation of Q(sigma, lambda) and Double...	14	Experimental	7	TeX
44	aweeraman/reinforcement-learning-continuous-control Continuous Control with deep reinforcement learning where the agent must...	14	Experimental	9	Python
45	VaradhKaushik/RL-models-for-Super-Mario-Bros This repository explores the application of three reinforcement learning...	13	Experimental	5	Jupyter Notebook
46	AugustUnderground/gace DEPRECATED. Use circus instead	13	Experimental	7	Hy
47	Unique-Divine/grid-world-plus A research project in vision-based deep reinforcement learning centered on...	12	Experimental	3	Python
48	cirovitale/smart-car Smart Mobility Unity simulation using Reinforcement Learning for autonomous...	12	Experimental	1	C#
49	mohamedrxo/DQN Here, I implement Deep Q-Learning (DQN) to train agents on various Gym...	11	Experimental	5	Jupyter Notebook
50	victor-iyi/openai-gym A Reinforcement Learning demo using the OpenAI's gym environment.	11	Experimental	2	Jupyter Notebook
51	malyvsen/wombat Minimalist, flexible Python reinforcement learning framework. Out-of-the-box...	10	Experimental	1	Jupyter Notebook
52	jeffasante/RL-PPO-SharpShooter Custom-built Proximal Policy Optimization (PPO) agent learns to master a 2D...	10	Experimental	1	Python