Unity-Technologies/ml-agents
Unity-Technologies/ml-agents has 19,818 GitHub stars and 4,516 forks. GitHot measured +1 stars in 24 hours. Last checked 2026-11-04 21:49 UTC. Last push 2026-10-30.
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.
Measured star growth
- in 24h
- +1
- in 7 days
- Collecting history
- in 15 days
- Collecting history
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
README.md
OriginalUnity ML-Agents Toolkit
(latest release) (all releases)
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.
Documentation
The ML-Agents package documentation is the primary documentation for ML-Agents. It includes installation instructions, version compatibility, features, tutorials, API references, and how to cite ML-Agents in your research.
Get started
To install ML-Agents and check which Unity and Python versions are compatible, refer to Install the ML-Agents Toolkit.
Contribute
To contribute, refer to Contribute to ML-Agents and the code of conduct.
Get help and give feedback
- For installation and setup problems, or discussions about how to set up or train your agents, create a thread on the Unity ML-Agents discussion forum.
- For other problems or feature requests, submit a GitHub issue.
For more community resources and information about privacy and in-editor analytics, refer to the ML-Agents package documentation home page.
Explore related projects
tensorflow/tensorflow
An Open Source Machine Learning Framework for Everyone
201,297 starshuggingface/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
168,525 starsAUTOMATIC1111/stable-diffusion-webui
Stable Diffusion web UI
165,239 starsComfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
144,962 stars