Skip to content
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

polish(nyp): fix unittest for trex training and collecting #144

Merged
merged 35 commits into from
Dec 14, 2021

Conversation

Will-Nie
Copy link
Collaborator

@Will-Nie Will-Nie commented Dec 9, 2021

Description

Change the mujoco env into cartpole env for test for the trex onppo algorithm

Related Issue

No mujoco env on test

TODO

Check List

  • merge the latest version source branch/repo, and resolve all the conflicts
  • pass style check
  • pass all the tests

@Will-Nie Will-Nie changed the title Trex algorithm feature(nyp): fix test for Trex combined with on policy rl algorithm Dec 9, 2021
@Will-Nie Will-Nie added the algo Add new algorithm or improve old one label Dec 9, 2021
@Will-Nie Will-Nie added this to the Inverse RL milestone Dec 9, 2021
@codecov
Copy link

codecov bot commented Dec 13, 2021

Codecov Report

Merging #144 (5756697) into main (a7de696) will increase coverage by 1.09%.
The diff coverage is 90.18%.

❗ Current head 5756697 differs from pull request most recent head 4e2d34f. Consider uploading reports for the commit 4e2d34f to get more accurate results
Impacted file tree graph

@@            Coverage Diff             @@
##             main     #144      +/-   ##
==========================================
+ Coverage   83.99%   85.09%   +1.09%     
==========================================
  Files         399      414      +15     
  Lines       30929    31861     +932     
==========================================
+ Hits        25979    27111    +1132     
+ Misses       4950     4750     -200     
Flag Coverage Δ
unittests 85.09% <90.18%> (+1.09%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
ding/entry/__init__.py 100.00% <ø> (ø)
ding/worker/buffer/deque_buffer_wrapper.py 22.53% <22.53%> (ø)
ding/worker/buffer/buffer.py 85.00% <85.00%> (ø)
ding/worker/buffer/middleware/group_sample.py 86.36% <86.36%> (ø)
ding/worker/buffer/middleware/use_time_check.py 90.32% <90.32%> (ø)
ding/worker/buffer/middleware/priority.py 92.63% <92.63%> (ø)
ding/worker/buffer/middleware/clone_object.py 94.11% <94.11%> (ø)
ding/worker/buffer/deque_buffer.py 94.24% <94.24%> (ø)
ding/worker/buffer/middleware/padding.py 96.00% <96.00%> (ø)
ding/worker/buffer/utils/fast_copy.py 97.43% <97.43%> (ø)
... and 23 more

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 147d56f...4e2d34f. Read the comment docs.

@PaParaZz1 PaParaZz1 changed the title feature(nyp): fix test for Trex combined with on policy rl algorithm polish(nyp): fix unittest for trex training and collecting Dec 14, 2021
@PaParaZz1 PaParaZz1 merged commit f089d02 into opendilab:main Dec 14, 2021
puyuan1996 pushed a commit to puyuan1996/DI-engine that referenced this pull request Apr 18, 2022
…#144)

* add trex algorithm for pong

* sort style

* add atari, ll,cp; fix device, collision; add_ppo

* add accuracy evaluation

* correct style

* add seed to make sure results are replicable

* remove useless part in cum return  of model part

* add mujoco onppo training pipeline; ppo config

* improve style

* add sac training config for mujoco

* add log, add save data; polish config

* logger; hyperparameter;walker

* correct style

* modify else condition

* change rnd to trex

* revise according to comments, add eposode collect

* new collect mode for trex, fix all bugs, commnets

* final change

* polish after the final comment

* add readme/test

* add test for serial entry of trex/gcl

* sort style

* change mujoco to cartpole for test for trex_onppo

* remove files generated by testing

* revise tests for entry

* sort style

* revise tests

* modify pytest

* fix(nyz): speed up ppg/ppo and marl algo unittest

* polish(nyz): speed up trex unittest and fix trex entry default config bug

* fix(nyz): fix same name bug

* fix(nyz): fix remove conflict bug(ci skip)

Co-authored-by: niuyazhe <niuyazhe@sensetime.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
algo Add new algorithm or improve old one
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants