These are the steps that I followed :
- Started training without any NNModel and ran it for (11 hours approx and 70k steps)
- Stopped training and generated “.nn” file.
- Relaunched Unity.
- Started training again with the previously generated file.
- The behaviour was different in both cases.
Is it because I didn’t let the agent complete the max_steps configured in the config? or is there some other reason for this.