ML-Agents
Some data may be outdated — see provenance labels.
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. observed · 2026-10-02
Health v2 · maintenance only
66/100
- Activity 97
- Release rhythm 8
- Longevity 100
Flags: no_license no_readme
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 3329
- days_rel: 413
- days_push: 21
- n_releases_24m: 1
Adoption not part of the score
19717 stars · 4501 forks observed · 2026-10-02
What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-19, confidence 0.97
Unity ML‑Agents is an open‑source toolkit that lets developers use Unity environments to train intelligent agents with deep reinforcement and imitation learning. It provides Python APIs, Unity‑side SDKs, and example environments for rapid experimentation.
Use cases
- train AI agents in Unity simulations
- apply reinforcement learning to game environments
- use imitation learning to model character behavior
- develop autonomous agents for robotics or virtual training
- benchmark RL algorithms in 3D worlds
- integrate trained ML models into Unity projects
When to choose
- You need a high‑fidelity 3D environment for RL research
- Your project already uses Unity as the simulation platform
- You want tight integration between Unity and Python training pipelines
- You require support for both reinforcement and imitation learning
When to avoid
- You are not using Unity or need a lightweight 2D environment
- You require a pure Python library without C# dependencies
- Performance constraints prevent running Unity in headless mode
Facets
library · maturity active
api-framework artificial-intelligence machine-learning windows cross-platform unity csharp reinforcement-learning imitation-learning ml-agents simulation macos linux desktop
9 sources
- homepage: https://unity.com/products/machine-learning-agents · fetched 2026-10-05 · 333b0d4d1d19
- site_page: https://unity.com/features/liveops · fetched 2026-10-05 · 233c57c4dc71
- site_page: https://unity.com/features/multiplayer · fetched 2026-10-05 · 5e0d1490294f
- site_page: https://docs.unity.com · fetched 2026-10-05 · 3ef51e67a898
- site_page: https://unity.com/features/collaboration · fetched 2026-10-05 · 7cee4905bf1e
- site_page: https://unity.com/features/multiplatform · fetched 2026-10-05 · cbe56df5dd47
- site_page: https://unity.com/features/ai · fetched 2026-10-05 · d27d59dd8b0d
- site_page: https://unity.com/roadmap · fetched 2026-10-05 · b38a8bca686c
- site_page: https://unity.com/faq · fetched 2026-10-05 · 97d41efe1c85
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| Unity-Technologies/ml-agents | main | 66 |
| Unity-Technologies/ml-agents-dodgeball-env | examples | 50 |
For agents
markdown · JSON · MCP: product_card(name="Unity-Technologies/ml-agents")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem