whatisgithub

What is ml-agents?

coac/ml-agents — explained in plain English

Analysis updated 2026-07-18 · repo last pushed 2018-05-15

C#Audience · researcherComplexity · 4/5DormantSetup · hard

In one sentence

Unity ML-Agents lets you train AI characters inside Unity games and simulations by letting them learn through trial and error rather than hand-coding behavior.

Mindmap

mindmap
  root((repo))
    What it does
      Train game AI
      Trial and error learning
      Unity plus Python
    Tech stack
      C#
      Unity
      Python
    Use cases
      Train NPCs
      Robot coordination research
      Test game mechanics
    Audience
      Researchers
      Game developers

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Train an NPC to play a game more intelligently through reinforcement learning.

USE CASE 2

Study how simulated agents or robot swarms learn to coordinate.

USE CASE 3

Use the example environments, like the balancing-ball demo, to learn the training workflow.

What is it built with?

C#UnityPython

How does it compare?

coac/ml-agentsanulman/docx-saxatrblizzard/vtmb-sbox-mounter
Stars—00
LanguageC#C#C#
Last pushed2018-05-15——
MaintenanceDormant——
Setup difficultyhardmoderatemoderate
Complexity4/54/53/5
Audienceresearcherdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1h+

Requires Unity plus a Python ML environment, project is still in beta with some experimental features.

Copy-paste prompts

Prompt 1
Show me how to set up a simple Unity environment and connect it to the Python training interface.
Prompt 2
Explain how an agent learns through rewards and trial and error in this toolkit.
Prompt 3
Walk me through the balancing-ball example environment included in this repo.
Prompt 4
What do I need to define in Unity for an agent to perceive its environment and take actions?

Frequently asked questions

What is ml-agents?

Unity ML-Agents lets you train AI characters inside Unity games and simulations by letting them learn through trial and error rather than hand-coding behavior.

What language is ml-agents written in?

Mainly C#. The stack also includes C#, Unity, Python.

Is ml-agents actively maintained?

Dormant — no commits in 2+ years (last push 2018-05-15).

How hard is ml-agents to set up?

Setup difficulty is rated hard, with roughly 1h+ to a first successful run.

Who is ml-agents for?

Mainly researcher.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.

What are similar repos?