How to install Unity ML Agents Release 19 in 2022 and build your own Machine Learning project

#unity #mlagents #ArtificialIntelligence #MachineLearning #ReinforcementLearning #AI #NeuralNetworks #gamedev

In this video, I will show you how to install ML-Agents Release 19 for Unity 2020.3 or later, step by step, to create your own Machine Learning project using Unity and Reinforcement Learning.

0:00 - Introduction
0:20 - Download and Install Anaconda
0:45 - Download ML-Agents Release 19 via GitHub
1:00 - Setup Anaconda Environment
3:05 - Create New Unity Project
4:15 - Install ML-Agents in Unity
5:00 - Import ML-Agents Examples
6:15 - Test ML-Agents with Push Block environment
6:30 - Start Training your own Neural Network
9:20 - Test your Neural Network in Inference Mode

In this video, I will show you how to install Unity ML Agent Release 19 in 5 simple steps:

1. Download and Install Unity Hub and Unity 2020.3 or later (not in the video)

2. Download and Install Anaconda

3. Download ML-Agents Release 19

4. Open an Anaconda Prompt and create a new environment and activate it:
conda create -n mlagents_R19 python=3.8
conda activate mlagents_R19

5. Install ML-Agents in your Anaconda Environment:
pip3 install -e ./ml-agents-envs
pip3 install -e ./ml-agents

6. Start Training using Proximal Policy Optimisation (PPO):

------

ML-Agents Release 19 Installation Guide:

ML-Agents Release 19 Getting Started:

[xSIXAX]

Thanks for the little introduction. It was very stupid to get all the right versions done but at the end it works and ill try out some stuff for my own projects :)

[ishan-singla]

As of 2nd April, 2023, if anybody's getting PROTOBUF error or something like this while trying to train mlagents, run the command with environment activated "pip install protobuf==3.19.6"

[keyhaven]

I have always had a question about mlagents: they randomly select actions at the beginning of training. Can we incorporate human intervention into the training process of mlagents to make them train faster? Is there a corresponding method in mlagents? Looking forward to your answer.

[vitotonello]

richtig geil. Hatte alles wieder vergessen :D

[AordatusExtra]

I am using 2021.3.22f1 and I am getting The type or namespace name 'Newtonsoft' could not be found (are you missing a using directive or an assembly reference?)

[charlesAcmen]

maybe you wont notice this comment, but i have to persist to say thank you bro, i successfully configured my mlagents env, but unfortunately due to new edition of unity or something else, i cant address all the errors mentioned in the console, but yeah, thank you again!

[karost]

just try Release 20 by follow your gide and it work! , Thanks

[Bosko_Ivkovic]

How did you stop the training at 9:15?

[ncom]

Thanks for this great tutorial.
Minor detail, if it's the first time, you may have an error "Module onnx is not installed!".
Just resolve it with : pip3 install onnx

[insertedfailed]

How do we stop the training properly at 9:12?

[mikhailhumphries]

Will you create more advanced videos on unity ml agents?

[goldenglowmaster]

How would you install and train sac instead of ppo

[throwoff]

Whenever I try to import Ml Agents folder in Project into the unity assets folder, it doesn't work it doesn't do anything absolutely anything

[Orm]

Thank you very much. Great video. You helped me a lot. Only problem was with current numpy version, so I had to downgrade it to 1.23.3 but everything else is up to date.

[toxian]

when I add mlagent example asset to unity it said " The type or namespace name 'Newtonsoft' could not be found (are you missing a using directive or an assembly reference?)" how to fix it?

[bikelife_gus]

release 20 is out and idk how to install it.

[mikhailhumphries]

We need to load models that we download in runtime from a webserver, and we execute it in a build (not in Editor), is it possible?
All the examples and code I find only work within Editor using the Resources Folder and the walk scene only works in the editor and we i try to build it, it reverts back to the default ONNX Model.

[eliudgonzalez]

Gracias bro... aunque antes había hecho varias preguntas, paso a paso las fui resolviendo, desde hace rato quería aprender a y utilizar MLAgent, pero siempre había un problema, pero este video me ayudo de muchas gracias, espero en un futuro puedas dar ejemplos haciendo proyectos desde 0.

Un gran abrazo

[nurhamidaljaddhi]

Thank you for this aamazing video, really enjoy to follow.
I already follow the instruction. However, I face a problem. When I start training the agent, the folder summaries cannot generated, so that I cannot move to visualize the result using tensorboard. Is there any steps I missing? Thank you.

[NoRemorseddly]

I keep getting the error: AttributeError: module 'numpy' has no attribute 'float' any idea what I can do to fix it?