Fix/madqn #362
Merged
Fix/madqn #362
Conversation
This file contains 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
jcformanek
requested review from
AsadJeewa,
mmorris44 and
RuanJohn
as code owners
1 task
Merge develop.
DriesSmit
previously approved these changes
Feb 11, 2022
There was a problem hiding this comment.
Amazing work @jcformanek!!:1st_place_medal: :fire: Lets get this in :slightly_smiling_face:
RuanJohn
approved these changes
Feb 11, 2022
|
Thanks guys. Sorry that this was a "Big Bang PR". I will make sure PRs are smaller in future 👍 |
KaleabTessera
approved these changes
Feb 11, 2022
arnupretorius
approved these changes
Feb 11, 2022
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Outdated suggestions cannot be applied.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.
What?
Did major refactoring to the MADQN code.
Implemented working system for value decomposition based algorithms such as VDN and QMIX.
Created a SMAC wrapper so that we can compare with pymarl since the PZ SMAC wrapper is functionally different.
Created environment wrappers that concat prev actions and agent ids to the observations.
Why?
Improved reliability and performance in the MADQN system.
VDN and QMIX were not working before.
SMAC wrapper, prev action wrapper and agent id wrapper let us compare better with pymarl.
How?
MADQN refactor.
New Value Decomposition system inherits from MADQN with additional, interchangeable
mixercomponent.Extra
[Any extra information.]