How to get done or terminal information in python code?

Hello. I have a question about python code for ML-Agents.
First, I want to ask that there is a plan for releasing python example code (getting_started.ipynb in previous versions).
There is no python example codes in ML-Agents 1.0 release 1 and release 2, so I am trying to use the getting_started.ipynb in version 0.15.1.
I fixed some parts of the codes, so I could run 1 step.
However, I couldn’t find where I can get done or terminal information.

In the following image, I checked that the step_result consists of DecisionSteps and TerminalSteps. However, there was no done or terminal information in step_result. So, I want to ask that how can I get done or terminal information of the agent in the python script.

Thank you.

Hey there! I’ll flag this for the team to take a look, and provide some insight.

Hi @mks0813 ,
We recently added some colab notebooks, linked here: ml-agents/docs at main · Unity-Technologies/ml-agents · GitHub
I think the first one is the equivalent of the old ipynb notebooks.

There’s also some testing code that we run here ml-agents/ml-agents/tests/yamato/scripts/run_llapi.py at release_3 · Unity-Technologies/ml-agents · GitHub to give you a better example of how stepping with the low level API works.