Train ML Agent on different levels

Unity Engine
, ,
1

Hi,
I’m currently developing an Agent for my racing game.

When I started training on my very complex first level, the agent made 2/3 of the track in 24 hours learning.

So I thought that I should train the agent on simple tracks first (a straight track, a simple round track,…)

But how do I train a previous trained model on a different game level?

Is “- - resume” the right approach or is there another command for learning on different environments?

For example is this right after the training on a previous different level?
mlagents-learn - -run-id=“PreviousRunId” --resume

Or is this the wrong approach and I should train different tracks simultaneously with multiple agents?

2

Hello. You can run resume to continue training a model on a new environment, but I would recommend having many different agents learning on different tracks simultaneously. This will prevent any possible catastrophic forgetting (Catastrophic interference - Wikipedia) which may take place if you try to train the model sequentially.

3

Thank you, I will give it a try. I’ve also seen that the karting micrograme uses multiple levels in parallel.