'Error running model trained on cloud on local machine
I trained a reinforcement learning model using a GPU instance from Lambda Labs cloud service. The library I used for training is stable_baselines3. When I try to run the model on my local machine I get the following error which I can't figure out why.
error:
AttributeError: Can't get attribute 'RandomNumberGenerator._generator_ctor' on <module 'gym.utils.seeding'
I ensure that the environment in which the model was trained is the same as the one on my local machine. Any ideas of why this is happening? When I train the model on my local machine it works just fine.
Solution 1:[1]
Check the gym versions on the cloud service compared to your local machine. I think the attribute you are looking for was added after 0.21.
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 | user18987397 |