New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
'>' not supported between instances of 'float' and 'NoneType' #122
Comments
The environments is a custom one, but I get the same error when launching CartPole. |
Which version of python are you using? |
I'm on 3.6.5 |
While the error occurs in a recurrent manner, the algorithm still functions.
But I thought best to find where lies the error. |
Do you use the most recent PyTorch/baselines/gym? I don't get this error for cartpole |
I think I do. Could it be something with Visdom maybe ? |
It doesn't look like a vizdom problem. Can you provide more information? Is your env on github? |
I tried this debug: def main():
torch.set_num_threads(1)
device = torch.device("cuda:0" if args.cuda else "cpu")
input('Entering viz')
if args.vis:
from visdom import Visdom
print(args.port)
viz = Visdom(port=args.port)
print(viz)
win = None
input('Exit') Here's the output:
It is indeed: https://github.com/Mehd6384/RL/tree/master/GymReacher |
Did you launch visdom in the background? python -m visdom.server For me it works for version '0.1.8.5'. |
I did and I'm on the same version here which is strange. Overall, the algorithm worked and returned a functional policy, I was just surprised by this message |
Ok. Then let's keep the issue open. Also could you create a similar issue for visdom repository? It looks like the problem is in visdom itself. |
The issue is already there |
Hello,
When running PPO various environments, I get the following error message:
'>' not supported between instances of 'float' and 'NoneType'
. I narrowed the error to the point where the Visdom server is initialized but I can't figure out why this happens.Also, I used the following command to launch the training:
python main.py --env-name "mreacher-v0" --algo ppo --use-gae --lr 2.5e-4 --clip-param 0.1 --value-loss-coef 1 --num-processes 8 --num-steps 128 --num-mini-batch 4 --vis-interval 1 --log-interval 1
Thanks !
The text was updated successfully, but these errors were encountered: