Feat/maddpg obs optim #459
Merged
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
AsadJeewa
requested review from
arnupretorius,
KaleabTessera,
DriesSmit,
mmorris44,
RuanJohn and
jcformanek
as code owners
|
By design, DDPG only uses the Critic loss to update the shared observation networks hence the results of previous investigations were inconclusive Neptune Results This has opened up 2 further investigations #481 & #482 |
arnupretorius
previously approved these changes
Apr 20, 2022
DriesSmit
previously approved these changes
Apr 21, 2022
KaleabTessera
suggested changes
Apr 21, 2022
…deepai/Mava into feat/maddpg_obs_optim
arnupretorius
approved these changes
Apr 21, 2022
KaleabTessera
approved these changes
Apr 21, 2022
DriesSmit
approved these changes
Apr 22, 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Outdated suggestions cannot be applied.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?
Temp branch for maddpg experiments
Why?
Benchmark to confirm updating observation network with only critic is best
How?
Benchmark with only critic gradients and previous (both actor and critic) and confirm no regression