Batch and async training do not work with macOS/Windows and Python >= 3.8

pfnet / pfrl

PFRL: a PyTorch-based deep reinforcement learning library

MIT License

1.19k stars 157 forks source link

Batch and async training do not work with macOS/Windows and Python >= 3.8 #123

Open marioyc opened 3 years ago

marioyc commented 3 years ago

In Python 3.8 the default mode of multiprocessing for macOS was changed

For reference: https://github.com/chainer/chainerrl/issues/572

elbamos commented 2 years ago

I was able to workaround this by calling mp.set_start_method('fork') before main() in the example scripts.

shreyassr123 commented 4 months ago

I am not able to run train_dqn_batch_ale.py. Further, mp.set_start_method('fork') is also not working for me. I am getting the following error : AttributeError: Can't pickle local object 'main..make_env'