made coin game compatible with iql_rnn #107
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
|
hey thanks for opening this :) we're busy with neurips rebuttals atm but will come back to this after! |
|
Hey! just took a look and it looks good but could you add a flag for shared vs individual rewards? @Dronie |
Done :) |
amacrutherford
approved these changes
Sep 9, 2024
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Outdated suggestions cannot be applied.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.
Slightly changed the way observations, rewards, dones and infos are processed/returned to make coin game compatible with iql_rnn (and potentially others but this is the only algorithm I tested).
Also added line 352 which allows for shared rewards (each agent's reward becomes the sum of their individual rewards) but not yet integrated in a nice way.
See plots for training results (using same configs as in ql_rnn_mpe):
Also see gifs of trained policies in action (10 episodes each):
Default (individual) rewards:
Shared rewards:
NB: have not done unit tests as this is only a minor change to an existing environment - let me know if this is an issue!