How to Log, Explore, Compare the RL Agent Training Metadata
What will you learn?
How you can log, explore and compare the RL agent training metadata in Neptune.
-
Introduction to the CartPole RL problem
-
How to connect to Neptune and create a run?
-
Logging metadata in a hierarchical structure
-
How to log charts, metrics, agent-specific metadata to Neptune?
-
How to log images and other artifacts to Neptune?
-
Logging a series of images
-
Uploading the model
-
What will the results look like in the Neptune UI?
-
Some visualizations of the input screen and the training episode
-
Exploring the dashboards
Read this article
Couldn’t find the use case you were looking for?
Just get in touch, and our ML team will create a custom demo for you.