Is this repo unfinished and i’m digging too soon into it?
Pretty much yes
But you are free to start experimenting with it anyway! The basic idea is that you point
train.py to an experiment file.
So in the following example:
python ./train.py -f experiments/flatland_random_sparse_small/global_obs_conv_net/ppo.yaml
you are using this file: https://gitlab.aicrowd.com/flatland/neurips2020-flatland-baselines/blob/master/experiments/flatland_random_sparse_small/global_obs_conv_net/ppo.yaml
In there you have
num_gpus: 1 and
num_workers: 7 so to run that you’ll need at least a GPU and at least 8 cores (7 workers + 1 main thread). Just tweak these values to match your hardware!
But yeah this is still mostly undocumented and very experimental so expect rough edges