Closed call-me-anything-you-want closed 8 months ago
If I remember correctly, you just need to manually change the output directory and training dataset in overcooked_ai/src/human_aware_rl/imitation/reproduce_bc.py
so it uses CLEAN_2019_HUMAN_DATA_TEST
and saves the output model to the imitation/bc_runs/test
dir. The human proxy model is basically another behavior cloning model trained with the held-out data to evaluate against other models at test time.
@jyan1999 Thanks for the help, I've successfully obtained the human proxy models following your instructions.
This might be a silly question. But I can't find the source code for training a human proxy model. I noticed that
overcooked_ai/src/human_aware_rl/imitation/reproduce_bc.py
can train bc models which are then stored inimitation/bc_runs/train
. But theovercooked_ai/src/human_aware_rl/ppo/evaluate.py
requires models stored inimitation/bc_runs/test
. Which file can I run to generate corresponding hp models?