The progress bar doesn't increase at all

[seolhokim]

after pip install -r requirements.txt,

I ran python train.py --config configs/maml/halfcheetah-vel.yaml --output-folder maml-halfcheetah-vel --seed 1 --num-workers 8

but progress doesn't increase after a day. 0%| | 0/500 [00:00<?, ?it/s]

I found that is waiting valid_futures. https://github.com/tristandeleu/pytorch-maml-rl/blob/21d4ba1ccd300a403928e6db553c9529bcc3fbdf/maml_rl/metalearners/maml_trpo.py#L96

but how can i fix it?

[seolhokim]

It is too difficult for me to find the exact line where the error occurs because even one worker is stuck at another point.

[NagisaZj]

I am facing the same problem. Here's my package versions (python 3.6):

akro                   0.0.8
astunparse             1.6.3
attrs                  21.2.0
cached-property        1.5.2
certifi                2021.5.30
cffi                   1.15.1
clang                  5.0
cloudpickle            2.2.0
cma                    2.7.0
Cython                 0.29.32
dataclasses            0.8
decorator              4.4.2
Deprecated             1.2.13
dm-tree                0.1.6
dowel                  0.0.3
fasteners              0.18
filelock               3.4.0
flatbuffers            1.12
future                 0.18.2
glfw                   2.5.5
google-auth            1.35.0
gym                    0.21.0
imageio                2.15.0
importlib-metadata     4.8.3
importlib-resources    5.4.0
jsonschema             3.2.0
keras                  2.6.0
lockfile               0.12.2
mkl-fft                1.3.0
mkl-random             1.1.1
mkl-service            2.3.0
msgpack                1.0.3
mujoco-py              2.0.2.9
networkx               2.5.1
numpy                  1.19.2
olefile                0.46
opt-einsum             3.3.0
Pillow                 8.4.0
pip                    21.2.2
psutil                 5.8.0
pycparser              2.21
pyrsistent             0.18.0
PyWavelets             1.1.1
PyYAML                 6.0
scikit-image           0.17.2
setproctitle           1.2.2
setuptools             58.0.4
six                    1.16.0
tabulate               0.8.9
tensorboardX           2.4.1
tensorflow-probability 0.15.0
termcolor              1.1.0
tifffile               2020.9.3
torch                  1.7.0
torchaudio             0.7.0a0+ac17b64
torchvision            0.8.0
tqdm                   4.64.1
typing-extensions      3.7.4.3
wheel                  0.37.1
zipp                   3.6.0

[WenliangGuo]

Did you solve this problem?

[shenmuxin]

I have the same question. I try to run this code in Ubuntu 20.04. sjh  battle  …/pytorch-maml-rl  master ◔  maml  python train.py --config configs/maml/halfcheetah-vel.yaml --output-folder maml-halfcheetah-vel --seed 1 --num-workers 8 0%| | 0/500 [00:00<?, ?it/s]

Did somenoe fix it ? Please let me know. Thanks!