Implementation of a CrossQ agent in Jax and PyTorch #283
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
…ntation of CrossQ
Author
|
@Toni-SM Here is the pull request we discussed, if you could give it a look |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
This is not an actual PR as of yet.
I have tried adding a CrossQ agent to this library without much success and require some assistance, especially with the Jax implementation as I have never actually used the framework and am having trouble understanding how it works behind the scenes.
The following links are provided as reference implementations of the algorithm in another library:
Both of these implementations are based on the Stable-baselines3 RL library which can be found here : https://github.com/DLR-RM/stable-baselines3
This PR provides an initial but incomplete Jax implementation as well as a complete but unstable Torch implementation. However I cannot, for the life of me, find what is wrong with the Torch implementation (the agent does not seem to be learning, and the mean reward spikes up and down erratically).