lukehollis/three-mlagents
Three.js + Torch implementation of Unity's ML-Agents framework for agent training and visualization in browser
This project allows researchers and engineers to design, visualize, and train intelligent agents within a web browser using 3D environments. You can input custom environment rules and agent behaviors, then observe the agents learning and interacting in simulations like navigating mazes or controlling vehicles. It's designed for machine learning practitioners, robotics engineers, and anyone exploring reinforcement learning in interactive 3D spaces.
Use this if you want an accessible, browser-based platform to prototype and visualize reinforcement learning agents in various 3D simulated environments.
Not ideal if you need high-performance, large-scale training for production-ready autonomous systems or if you require deep integration with a full-featured game engine.
Stars
32
Forks
1
Language
Python
License
—
Category
Last pushed
Dec 31, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lukehollis/three-mlagents"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Unity-Technologies/obstacle-tower-env
Obstacle Tower Environment
UnityTechnologies/MachineLearningRoguelike
A small Roguelike game that uses Machine Learning to power its entities. Originally used in...
CoderOneHQ/ultimate-volleyball
3D RL Volleyball environment built on Unity ML-Agents
kaiergin/runescape-ML
Train computer vision models to complete clicking tasks by learning from your recorded data
Naton1/osrs-pvp-reinforcement-learning
Train a neural network to PvP in Old School RuneScape using reinforcement learning.