ml-agents and UnrealMLAgents
ML-Agents is a direct competitor that provides the same reinforcement learning training framework functionality, but UnrealMLAgents is a specialized port attempting to replicate that capability for Unreal Engine rather than Unity, making them mutually exclusive choices for the same use case depending on which game engine you're using.
About ml-agents
Unity-Technologies/ml-agents
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Implements PyTorch-based algorithms (PPO, SAC, MA-POCA) for single and multi-agent scenarios, with support for imitation learning, curriculum learning, and environment randomization. Provides native cross-platform inference through its Inference Engine and exposes Unity environments as standard Python APIs (Gym, PettingZoo) for seamless integration with the broader ML ecosystem. Enables on-demand agent decision-making and concurrent training across multiple environment instances for scalable experiment iteration.
About UnrealMLAgents
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.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work