Upgrade to RLLib 1.3 and improvements around amTFT #12
Conversation
This file contains hidden or 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)
Renaming module tune_analysis into exp_analysis. SOS: add a few logs Welfare_coordinator: fix ordering in the set of welfare function sets. Env mixing: started adding NPlayersNContinuousActionsInfoMixin (not debugged) Env: started adding the SimpleBargaining env (not debugged) Env: removed the MixedMotiveCoinGame (not the MCPCG/SSDMMCG env) LOLA-PG: allow option to filter runs by speeds achieved LOLA-PG: both players can pick the same coin always Meta games: add the negotiation environment. Meta games: add the uniform solver. Scripts: add script to add create bar charts Scripts: update script to compute mean and std err from saved results. Scripts: add script to plot meta policies & joint meta policies experiment_analysis module: added a few helper functions FrozenTunePolicy: add callback to call policy reset at the start of each episode. PSRO: add PSRO hardcoded PSRO: started to add PSRO from OpenSpiel
Add the OpenSpiel version of the SimpleBargaining env. Add logs to compute the % of coordination in the welfare_coordination.py Add script to generate the scatter plots
Add cross experiments between meta solvers. Add evaluation of exploitability.
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.
No description provided.