Hello,
I’m trying to do hyperparameter tuning with Optuna for my Breakout agent. This is the simple example given in the doc :
python train.py --algo ppo --env MountainCar-v0 -n 50000 -optimize --n-trials 1000 --n-jobs 2 \
--sampler tpe --pruner median
Should I change the number of timesteps ? According to what ? And what about n-jobs ?
Best regards and thanks in advance for the help,