Hey everyone!
I’ve been working on a Deep Reinforcement Learning framework for game engines, and I’m excited to share UnrealMLAgents! This project is an ongoing port of Unity ML-Agents to Unreal Engine, bringing similar reinforcement learning capabilities to a new environment.
GitHub: GitHub - AlanLaboratory/UnrealMLAgents: The Unreal ML Agents Toolkit is an open-source project that enables Unreal Engine games and simulations to serve as environments for training intelligent agents using deep reinforcement learning. This project is a port of Unity ML-Agents, adapted to work within Unreal Engine.
Documentation: UnrealMLAgents documentation - UnrealMLAgents 1.0.0 documentation
For those unfamiliar with ML-Agents, it’s a framework from Unity that lets you train AI agents using reinforcement learning. It allows AI to learn from its environment, make decisions, and improve over time, whether for game AI, robotics, or simulations.
I wanted to bring these capabilities to Unreal Engine, so I started porting ML-Agents’ core features. Right now, UnrealMLAgents includes:
- Ray perception sensors for detecting the environment
- Custom actuators and sensors for flexible agent design
- Python communication to train agents externally
- Multi-agent support for handling complex simulations
It’s still a work in progress, and I’d love feedback from others interested in AI research, robotics, or game AI!If you like it, please star it on GitHub 
and feel free to join my Discord to chat, share ideas, or follow updates:
Discord: discord.gg/XNNJFfgw6M
Youtube: https://www.youtube.com/@AlanLaboratory
Looking forward to hearing your thoughts!
