You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am trying to create a GPU-based environment where a model is being trained say resnet18 where the number of environment can be greater than 1. I am not familiar with Jax but I am planning to learn it. However, I want to see how feasible this is with PureJaxrl before I start this voyage.
The text was updated successfully, but these errors were encountered:
@luchris429 Thanks for your response. I want to create an adaptive learning rate controller agent. I want the the environment step to involve training and evaluating a model. The action at the end of each step is to adjust the learning rate. How can I easily parallelize this for multiple environments?
I am trying to create a GPU-based environment where a model is being trained say resnet18 where the number of environment can be greater than 1. I am not familiar with Jax but I am planning to learn it. However, I want to see how feasible this is with PureJaxrl before I start this voyage.
The text was updated successfully, but these errors were encountered: