forked from Danielhp95/Regym
-
Notifications
You must be signed in to change notification settings - Fork 2
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Develop sad crossplay #1
Open
Danielhp95
wants to merge
47
commits into
develop-SAD
Choose a base branch
from
develop-SAD-crossplay
base: develop-SAD
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
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
performance metrics from test episodes
episode length or mean returns...)
+ updated ActorCriticNet and derived classes to rnn/frame_state standards. + updated trajectory gif plotter with celluloid. + added a parameterized render fn to VecEnv. + added residual/skip connections to some network bodies to bypass RNNs.
…rder to make sure it won't fail silently, just in case...
…entialGym. TODO: implement and test metrics. TODO: parallelised rl loop and supervised learning loop test.
IN PROGRESS: debugging of multi-step CIC metric: cannot differentiate between comm. and action-only rule-based agents...
+ needed to add a query method to agents in order to deal with computing losses using agents outside of agents' methods.
+ update marl_loop to new dict-outputting vec-env [TODO: test further...]
…a sequence, as done by R2D2 (but not DQN...).
…R... (no sequence of experience to handle during loss computation...) + updating final HER strategy in HER wrapper v2.
…agents. + all comaze metric module have a deterministic trigger.
+ implemented OP fix attempt. TODO: debug...
…dules biasing the main agents. + implemented some biasing modules for S2B.
…y losses modules. + added a multi reconstruction module.
+ fixed issue with test_agent fn's returning total return in place of total int return.
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.
Finished coding cross-play matrix computation as defined in "Other-Play" for Zero-Shot Coordination, Hu et al