Help on Vision-Input and RNN layer #76
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hey,
based on the latest implementation #73, I tried to add an additional RNN layer to the neural network.
I do not have any experience with implementing neural networks, the code is now running without error messages, but the training does not work. I would be grateful for help.
I am using IsaacLab and the black graph is the training without visual information and using the current ActorCriticRecurrent implementation using 4096 robots in parallel. The blue graph is using the new implementation using 512 robots with the same observations and additional camera inputs.
When comparing the graphs in regards to the number of robots, the result at 2000 episodes should be the same as at 250 episodes.