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
Upgrade to use RLLib master (almost v1.3). #10
Open
Manuscrit
wants to merge
15
commits into
master
Choose a base branch
from
upgrade_from_rllib_1_0_0_to_rllib_master
base: master
Could not load branches
Branch not found: {{ refName }}
Could not load tags
Nothing to show
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and old review comments may become outdated.
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
Remove use lock_replay during training (must not use it in LTFT). Create submodule marltoolbox.utils.log. Move methods to summarize a model into an helper class. use before_init_loss instead of after_init (policy class factory arg).
Fix some tests. Add augmented R2D2. Add examples with R2D2. Add some end to end tests for amTFT vs exploiter, meta game and R2D2.
Fix speed performance issue in entropy computation. Some refactoring of configs and hyperparameters (DQN, R2D2, LOLA-PG).
Tune HP for R2D2. Few corrections. Few style changes.
Partial refactoring of the coin game envs tests. Add logging & plot of exploration temperature.
…than 2. Add rolling average for the LOLA-PG reward centering and normalization.
- punishment helped in CGs - customizable matrix game - coop coins log in vectorized MCPCG
…, replicator dynamic)
Add the "punishment helped" option in vectorized_ssd_mm_coin_game.py. Add new plots by defaults in cross an self play evaluation. Add script to plot bar chart summary figure.
…ns (instead of 2 or 3 for LOLA-Exact and instead of 2 for SOS-Exact)
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.
Remove use lock_replay during training (must not use it in LTFT).
Create submodule marltoolbox.utils.log.
Move methods to summarize a model into an helper class.
use before_init_loss instead of after_init (policy class factory arg).