v0.9.1 - Gymnasium and Mujoco #324
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
* change opencv dependency to headless and upgrade to version 4 * revert test changes
* Release/0.8.2 (#276) * change opencv dependency to headless and upgrade to version 4 (#275) * change opencv dependency to headless and upgrade to version 4 * revert test changes * version 0.8.2 * switch to gymnasium and update imports * update state and state test * update atari and duplicate env * delete direct atari model test * update vector env * support legacy pybullet env * update multiagent pettingzoo * fix multi-agent atari * fix ma atari preset test * fix single_env_experiment tests * update parallel env experiment test * update multiagent env experiment test * run formatter * remove legacy gym import * add legacy gym dependency * specify pybullet gym dependency correctly * update to pong_v3 in multiagent integration test
* add mujoco depnedency * add MujocoEnvironment * fix integration tests * linting * update docs version number
* all scripts to all package * fix watch scripts * update watch script and add test * formatting * compute sem correctly * fix multiagent atari watch * add additional random seed * explicitly seed multiagent environment * make test less flakey
* add __call__ method to Builder API and unit tests * formatting
* loosen requirements of mujoco test * log training episode length * update parallel env training episode length tests * update single env episode length tests * log test episode length in single env experiment * remove unwanted print from tests * run formatter * print episode length to console during training
* add entropy_backups hyperparameter to SAC * run formatter
* use black formatter * add isort * remove unused imports * add missing isort import
* fix key error warnings * run formatter * remove unused import
* update publish workflow and add alpha tag * make sure setuptools and wheel are installed before publish * add the required id-token permission * update alpha version number
* add save_freq argument and refactor scripts * run formatter * fix test
* add initial add_hparams implementation * add add_hparams to logger interface * remove commit hash from run name * re-organize tensorboard tags * remove comet logger * remove additional comet logger references * remove logger kwarg * fix multiagent env logging * run formatter * fix SingleEnvExperimentTest * update parallel env test * run formatter * update multiagent env experimnet * fix softmax test problem * update torch version in workflows * fix integration tests * remove unwanted print * run formatter
* sample actions for SacTest agent * update sac default hyperparameters * update ddpg default hyperparameters * fix add_summary bug * use more standard hyperparameters for ddpg and sac * remove time body and adjust discount factor * adjust sac default hyperparameters * run formatter
* upgrade/adjust dependencies * adjust required depenencies * change maximum python version
…321) * add swig setup dependency and remove unrar/swig from github scripts * remove box2d dependency * remove box2d envs from tests
* update benchmarks files * merge * use humanoid instead of swimmer * make logdir match file name * update torch version to minimum version supporting global_step in add_hparams * update torch version for add_hparams update * adjust slurm usage * clip sac log_std * adjust ddpg hyperparameters * lower python version for deployment * revert benchmark code to include all agents/envs * rename benchmarks * change initial sac temperature * change pybullet logdir to match * run linter * add new benchmark results * update docs
* update setup.py * fix sphinx warnings * edit handling of docs dependencies * update docs to latest * run formatter * correct getting started doc * remove script imports * remove dev installation from .readthedocs.yml * fix localhost link
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.
Version 0.9.1. Updates several of the major dependencies, including: