# 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.

Repository: https://github.com/Unity-Technologies/ml-agents
Canonical: https://ross.abutalabs.com/products/ml-agents
Homepage: https://unity.com/products/machine-learning-agents
Language: C#
License: NOASSERTION
License Family: other
Topics: reinforcement-learning, unity3d, deep-learning, unity, deep-reinforcement-learning, neural-networks, machine-learning
Last push: 2026-08-25T08:41:37+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 13, longevity 100
- inputs: {"age_days": 3281, "days_push": 8, "days_rel": 365, "gap_med": 332, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 19647, forks 4484 (observed 2026-08-28T04:11:29.060101+00:00)

## What it is
The Unity Machine Learning Agents Toolkit (ML-Agents) lets Unity games and simulations serve as environments for training intelligent agents with deep reinforcement learning, imitation learning, and neuroevolution via a PyTorch-based Python API. It ships with 17+ example environments, multi-agent and self-play support, curriculum learning, and cross-platform inference for trained models.

## Use cases
- train NPC behavior for Unity games with reinforcement learning
- train multi-agent cooperative or competitive agents in a 3D simulator
- learn policies from human demonstrations via imitation learning
- run RL research experiments in Unity environments from Python
- wrap Unity environments as gymnasium environments for existing RL libraries
- use curriculum learning and environment randomization to train robust agents
- automated game build testing with trained agents

## When to choose
- you develop games or simulations in Unity and want intelligent agents
- you need multi-agent, self-play, or imitation learning in a 3D engine
- you want a free, well-documented RL environment platform with example scenes
- you need cross-platform inference of trained models inside Unity

## When to avoid
- your project does not use Unity as the simulation environment
- you need general-purpose RL without a game engine (use Gymnasium or similar)
- you require cutting-edge research algorithms not among PPO, SAC, MA-POCA, BC, or GAIL
- you cannot use Python and PyTorch for training

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, reinforcement-learning, deep-learning, simulation, sdk
- domain: reinforcement-learning, machine-learning, simulation, artificial-intelligence
- platform: game-engine, python, cross-platform
- tags: unity, pytorch, imitation-learning, multi-agent, npc-behavior, curriculum-learning, gym-environments, game-development

## Member repositories
- Unity-Technologies/ml-agents (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:29.060101+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:59:53.369470+00:00, confidence not recorded.
  - readme: https://github.com/Unity-Technologies/ml-agents (fetched 2026-08-28T04:11:29.060101+00:00, sha abd28bbe573d)
  - homepage: https://unity.com/products/machine-learning-agents (fetched 2026-08-29T07:58:23.376354+00:00, sha aa029ba48245)
  - site_page: https://unity.com/features/collaboration (fetched 2026-08-29T07:58:23.379975+00:00, sha cad621e9760e)
  - site_page: https://unity.com/features/multiplatform (fetched 2026-08-29T07:58:23.381870+00:00, sha 2449aa9cdd6b)
  - site_page: https://unity.com/features/liveops (fetched 2026-08-29T07:58:23.384084+00:00, sha 08535bc492a2)
  - site_page: https://unity.com/features/multiplayer (fetched 2026-08-29T07:58:23.386009+00:00, sha a1d8686f7179)
  - site_page: https://docs.unity.com (fetched 2026-08-29T07:58:23.388048+00:00, sha 3ef51e67a898)
  - site_page: https://unity.com/features/ai (fetched 2026-08-29T07:58:23.394412+00:00, sha a552b25d5458)
  - site_page: https://unity.com/roadmap (fetched 2026-08-29T07:58:23.390058+00:00, sha e647dc2f4252)
  - site_page: https://unity.com/faq (fetched 2026-08-29T07:58:23.392025+00:00, sha 3ecf5af1eaae)
- Data as of 2026-08-30T08:39:29.467469+00:00.