Please enable JavaScript.
Coggle requires JavaScript to display documents.
ML AGENT TOOLKIT FOR UNITY (Dépôt GIT (https://github.com/Unity…
ML AGENT TOOLKIT FOR UNITY
Dépôt GIT
https://github.com/Unity-Technologies/ml-agents
Documentation
Detailled guide
Getting Started with the 3D Balance Ball Environment
INSTALLATION
Installing ML-Agents Toolkit for Windows
Step 1: Install Python via Anaconda
Télécharger ANACONDA
Installation pour Windows
Setting environment var account
%UserProfile%\Anaconda3\Scripts
%UserProfile%\Anaconda3\Scripts\conda.exe
%UserProfile%\Anaconda3
%UserProfile%\Anaconda3\python.exe
INSTALLATION OF PYTHON
AND ANACONDA
Step 2 : Setup and Activate a New Conda Environment
conda create -n ml-agents python=3.6
activate ml-agents
pip install tensorflow==1.7.1
Step 3: Install Required Python Packages
structure
ml-agents
contains Python packages which provide trainers and a Python API to interface with Unity.
gym-unity
contains a package to interface with OpenAI Gym.
UnitySDK
contains the Unity Assets to add to your projects. It also contains many example environments to help you get started.
environnements to
start
cd C:\Users\XEYD730\ml-agents\ml-agents
pip install -e .
INSTALLATION INSTRUCTIONS - for Linux and Mac
Understanding the Unity Environment (3D Balance Ball)
BASIC
GUIDE
Acces
Setting up the ML-Agents Toolkit within Unity
Open option at the beginning
locate the UnitySDK
Edit > Project Settings > Player
Expand the Other Settings section
elect Scripting Runtime Version to Experimental (.NET 4.6 Equivalent or .NET 4.x Equivalent)
Save project
Setting up TensorFlowSharp
TensorFlow Sharp Plugin
Jupyter
FAQ
Frequently Asked Questions
Environment Connection Timeout
Version
0.6
DOCUMENTATION