|
|
|
|
|
|
|
particularly when debugging agent behaviors. You can learn more about using |
|
|
|
the broadcasting feature [here](Feature-Broadcasting.md). |
|
|
|
|
|
|
|
* **Docker Set-up (Experimental)** - To facilitate setting up ML-Agents |
|
|
|
without installing Python or TensorFlow directly, we provide a |
|
|
|
[guide](Using-Docker.md) on how |
|
|
|
to create and run a Docker container. Due to limitations on rendering visual |
|
|
|
observations, this feature is marked experimental. |
|
|
|
|
|
|
|
* **Cloud Training on AWS** - To facilitate using ML-Agents on |
|
|
|
Amazon Web Services (AWS) machines, we provide a |
|
|
|
[guide](Training-on-Amazon-Web-Service.md) |
|
|
|
on how to set-up EC2 instances in addition to a public pre-configured Amazon |
|
|
|
Machine Image (AMI). |
|
|
|
|
|
|
|
## Summary and Next Steps |
|
|
|
|
|
|
|
To briefly summarize: ML-Agents enables games and simulations built in Unity |
|
|
|
|
Marwan Mattar