merge code #1
Merged
merge code #1
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
* feature(zlx): Support async reset for envpool env manager * fixbug(zlx): Add final_eval_reward in returned dict
* impala cnn encoder refactor. * Minor change.
* test(wyh):add plot test code * test(wyh):add plot test code * test(wyh):add compare two different PICS codes * test(wyh):add compare two different PICS * test(wyh):compare two different PICS
* feature(nyz): add pure ppo policy gradient policy * fix(nyz): fix flake8 style problem and remove redundant codes of continuous bc
* add infoNCE * refine infonce test * add dim * fix style and pytest * fix style and pytest * add dqn_dim test * fix style * refine descriptions * polish infoNCE & ST-DIM * polish stdim & infonce loss * fix style * fix codecov * fix import * add readme * update quick colab link * add buffer description * polish buffer api * polish buffer api
* fix bugs in dmc2gym env. * fix bugs of libOpenGL.so.0 cannot open shared object file. * fix bugs in base env manager in subprocess mode when resetting and rendering dmc envs. * fix dockerfile * backward compatibity for tb video logging Co-authored-by: ZHZisZZ <zhanhui@umich.edu>
* feature(pu): add board_gmaes env including tictactoe, gomoku, chess, go, atari * style(pu): yapf format * polish(pu): refactor * polish(pu): polish as review * polish(pu): move atari_muzero_env to dizoo/atari * polish(pu):polish as review * fix(pu): fix tictactoe expert action * polish(pu): polish board_games env * style(pu): yapf format
* draft steve * remove breakpoint * fix numerical instability * polish * polish STEVE * change flatten_batch -> fold_batch * change from VE to MVE in README.md * speed up mbrl test * Polish docstrings, create unsqueeze_repeat helper function * fix assertion bug
* add trex example * polish import * merge main
* polish(lisong): add sqil cosine similarity of expert and agent grad * polish(lisong): create SQILSACPolicy and add mujoco config * feature(lisong): add sqil_sac example * polish(lisong): use pendulum as demo env * polish(lisong):polish sqil_continuous example * polish(lisong): remove get config
* test(rjy):add discrete pendulum env * test(rjy):fix discrete pendulum env * test(rjy): change the parameter * test(rjy): revise the pend_dqn config * test(rjy): correct spelling mistakes * test(rjy): modify the format
…384) * dev(lwq) continuous examples: ddpg & td3 * dev(lwq) continuous examples: ddpg, d4pg & td3
* polish(lwq): polish VAE * remove base VAE class
* Discard message sent by self in redis mq * Set running flag of redis mq * Rename nng finished to running * Fix self._mq is none * Turn deque into list
* add c51/qrdqn/iqn newpipeline example * fix style
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.
Description
Related Issue
TODO
Check List