That worked really well. I added 5 traces and now they are avoiding other cars.
Would you recommend resetting them after they crash into another car (similar to when they go too far away from the spline)? At the moment, I keep them running because they usually recover from the crash.
However, this causes my avg_reward to look a bit odd. Avg_return looks okay though:
Another question: I tried
I tried the imitation learning (following the tutorial). I was able to record the data, but running the imitation learning fails after a bit, the last thing shown in the log is this:
Subproccess: Profile | Logging 0ms
Subproccess: Profile | Pushing Policy... 2ms
Subproccess: Profile | Pushing Encoder... 1ms
Subproccess: Profile | Pushing Decoder... 0ms
Subproccess: Profile | Training 371ms
After that, the editor freezes. No crash occurs.
I followed the tutorial, the only thing I changed is the Trainer File Name:
i
By default, this was set to train_ppo which causes an error though when doing imitation learning. This is on UE 5.5.
Edit: Also my setup for the “Make Imitation Trainer” looks a bit different (due to API changes between 5.5 and 5.4):
