use-transfer path error

use-transfer path error

[gabrieledcjr]

when using --use-transfer, it automatically finds the pretrained model for a very specific pretrained model. Also, it might be confusing, but you should use --transfer-folder instead of --pre-trained-model-folder. The pretrained-model-folder is used for something else.

So use --transfer-folder and I suggest specifying the path as you did. In the path, don't include /transfer_model folder as it is automatically appended. And you don't need the single quotes. So in your case, it should be

python3 a3c/run_experiment.py --gym-env=MsPacmanNoFrameskip-v4 --parallel-size=1 --max-time-step-fraction=1.0 --initial-learn-rate=0.0007 --rmsp-epsilon=1e-5 --grad-norm-clip=0.5 --use-mnih-2015 --unclipped-reward --transformed-bellman --use-transfer --append-experiment-num=1 --transfer-folder=/home/ubuntu/newrl/DeepRL/results/pretrain_models/MsPacmanNoFrameskip_v4_mnih2015_l2beta1E-04_clipnorm5E-01

Yes, that worked, thanks.