Rapid training of mlAgent units for modelling cover behaviour by inference. This scene links to an external python application over Unity TCP containing user-defined observations created in an academy for which the unit “brains” undergo training.
Setup the python environment following these steps:
In order to utilize this example, you’ll first need to acquire the following Unity ML-Agents Toolkit core components: ml-agents-0.15.1, ml-agents-env, and ml-agents-release_12. Next, add the ML Agents v1.0.7 python training environment, which can be obtained through the Unity Package Manager.
Make Sure RIDE_ML_AGENTS is defined in the project scripting defines.
After completion, open a command window prompt at:
Enter the commands:
To start the training programming, enter the following command:
Then hit play in the Unity scene ExampleTrainingTakeCover scene and you will see the agents begin to train.
To watch how effective the training is, open a new command prompt in /ml-agents/ml-agents-env and enter the following:
Utilize mlAgent for your scene with the ExampleTrainingTakeCoverML script and TrainingArea_TakeCoverML prefab that contains the TrainingArea_TakeCover script, floor/walls, cover, goals, Agent (script), Enemy, and mlAgent objects.
First, add ExampleTrainingTakeCoverML script to an object in your scene.
Next, import the TrainingArea_TakeCoverML prefab into your scene to train agents for cover behavior in conjunction with an external python application.
This prefab that contains the TrainingArea_TakeCover script, floor/walls, cover, goals, Agent (script), Enemy, and mlAgent objects.
Create a prefab variant of TrainingArea_TakeCover to begin constructing your own training environments.
Recommend building a comparison scene to evaluate two approaches to your problem set. See Behaviour Comparison as an example for how to structure a side-by-side comparison of agent behaviour.