Hi Dr Yuan, firstly, thank you for your great work! However, when I implement PPO,

Have you set the env variable as mentioned in README? <div class="snippet-clipboar

Implementation problem about pytorch-rl HOT 6 CLOSED

khrylx commented on August 23, 2024

Implementation problem

from pytorch-rl.

Comments (6)

pengzhi1998 commented on August 23, 2024

It seems that the computation of the network in the processes has been stuck for whatever reason. Is it caused by the PyTorch's version? (however I tried torch.0.4.0, the same problem happens)

from pytorch-rl.

Khrylx commented on August 23, 2024

Have you set the env variable as mentioned in README?

export OMP_NUM_THREADS=1

from pytorch-rl.

pengzhi1998 commented on August 23, 2024

Wow, it works this time, thanks! So this command will influence training in both CPU and GPU?

from pytorch-rl.

Khrylx commented on August 23, 2024

It will only affect CPU based training. I have added it in code:

PyTorch-RL/core/agent.py

Line 7 in 7206923

os.environ["OMP_NUM_THREADS"] = "1"

So you won't need to manually set it and it won't affect other programs.

from pytorch-rl.

pengzhi1998 commented on August 23, 2024

Thank you!!!

from pytorch-rl.

pengzhi1998 commented on August 23, 2024

Sorry to bother you Dr. Yuan, but I have one more question, that I didn't find termination or join operation for the processes in the code. Is there a need to join the workers after they have been used?

from pytorch-rl.

Recommend Projects