这是indexloc提供的服务，不要输入任何密码
Skip to content

Add TRPO policy #337

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 25 commits into from
Apr 16, 2021
Merged

Add TRPO policy #337

merged 25 commits into from
Apr 16, 2021

Conversation

ChenDRAG
Copy link
Collaborator

Only draft, open for discussion.

@ChenDRAG ChenDRAG requested a review from Trinkle23897 April 14, 2021 04:29
@ChenDRAG ChenDRAG marked this pull request as draft April 14, 2021 04:29
@codecov-io
Copy link

codecov-io commented Apr 14, 2021 •
edited
Loading

Codecov Report

Merging #337 (d42174e) into master (333b8fb) will increase coverage by 0.06%.
The diff coverage is 95.28%.

❗ Current head d42174e differs from pull request most recent head 2e5aa52. Consider uploading reports for the commit 2e5aa52 to get more accurate results
Impacted file tree graph

@@            Coverage Diff             @@
##           master     #337      +/-   ##
==========================================
+ Coverage   94.19%   94.25%   +0.06%     
==========================================
  Files          51       52       +1     
  Lines        3256     3362     +106     
==========================================
+ Hits         3067     3169     +102     
- Misses        189      193       +4
Flag Coverage Δ
unittests 94.25% <95.28%> (+0.06%) ⬆️

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

Impacted Files Coverage Δ
tianshou/data/collector.py 94.93% <ø> (ø)
tianshou/policy/modelfree/trpo.py 95.23% <95.23%> (ø)
tianshou/policy/__init__.py 100.00% <100.00%> (ø)
tianshou/trainer/onpolicy.py 97.05% <0.00%> (+1.47%) ⬆️

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 333b8fb...2e5aa52. Read the comment docs.

@ChenDRAG ChenDRAG mentioned this pull request Apr 14, 2021
Closed
@ChenDRAG ChenDRAG self-assigned this Apr 14, 2021
@ChenDRAG ChenDRAG marked this pull request as ready for review April 14, 2021 11:15
@Trinkle23897 Trinkle23897 linked an issue Apr 15, 2021 that may be closed by this pull request
TRPO policy support #190
Closed
@Trinkle23897 Trinkle23897 changed the title Add Trpo policy Add TRPO policy Apr 15, 2021
ChenDRAG
ChenDRAG commented Apr 15, 2021
View reviewed changes
Trinkle23897
Trinkle23897 previously approved these changes Apr 15, 2021
View reviewed changes
Trinkle23897
Trinkle23897 reviewed Apr 16, 2021
View reviewed changes
Trinkle23897
Trinkle23897 reviewed Apr 16, 2021
View reviewed changes
@ChenDRAG
Copy link
Collaborator Author

Finished I think

@Trinkle23897 Trinkle23897 merged commit 5057b5c into thu-ml:master Apr 16, 2021
@Trinkle23897 Trinkle23897 linked an issue Apr 16, 2021 that may be closed by this pull request
Plans of implementing 3 classic model-free algorithm (TRPO/TNPG/ACKTR), and benchmarking them in mujoco settings #338
Closed
BFAnas pushed a commit to BFAnas/tianshou that referenced this pull request May 5, 2024
@ChenDRAG
Add TRPO policy (thu-ml#337)
60ea776
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Trinkle23897 Trinkle23897 Trinkle23897 approved these changes

Assignees

@Trinkle23897 Trinkle23897

@ChenDRAG ChenDRAG

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Plans of implementing 3 classic model-free algorithm (TRPO/TNPG/ACKTR), and benchmarking them in mujoco settings TRPO policy support
3 participants
@ChenDRAG @codecov-io @Trinkle23897