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

set policy.eval() before collector.collect #204

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

Merged
merged 2 commits into from
Sep 6, 2020
Merged

set policy.eval() before collector.collect #204

merged 2 commits into from
Sep 6, 2020

Conversation

Trinkle23897
Copy link
Collaborator

No description provided.

@Trinkle23897 Trinkle23897 linked an issue Sep 5, 2020 that may be closed by this pull request
8 tasks
@codecov-commenter
Copy link

codecov-commenter commented Sep 5, 2020

Codecov Report

Merging #204 into master will not change coverage.
The diff coverage is 87.50%.

Impacted file tree graph

@@           Coverage Diff           @@
##           master     #204   +/-   ##
=======================================
  Coverage   94.13%   94.13%           
=======================================
  Files          40       40           
  Lines        2455     2455           
=======================================
  Hits         2311     2311           
  Misses        144      144           
Flag Coverage Δ
#unittests 94.13% <87.50%> (ø)

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

Impacted Files Coverage Δ
tianshou/trainer/onpolicy.py 95.52% <75.00%> (ø)
tianshou/trainer/offpolicy.py 100.00% <100.00%> (ø)

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 34f714a...11b76d2. Read the comment docs.

@Trinkle23897 Trinkle23897 changed the title set policy.eval() when in collector.collect set policy.eval() before collector.collect Sep 5, 2020
youkaichao
youkaichao previously approved these changes Sep 5, 2020
@Trinkle23897 Trinkle23897 merged commit 8bb8ecb into thu-ml:master Sep 6, 2020
@Trinkle23897 Trinkle23897 deleted the fix-policy-train branch September 6, 2020 08:20
Leeqh666 added a commit to Leeqh666/tianshou that referenced this pull request Sep 6, 2020
set policy.eval() before collector.collect (thu-ml#204)
Trinkle23897 added a commit to danagi/tianshou that referenced this pull request Sep 11, 2020
Trinkle23897 added a commit that referenced this pull request Sep 12, 2020
- replace DiagGuassian with Independent(Normal) (pytorch has already supported this)
- detach alpha from autograd
- add value/alpha to result (more informational)
- revert #204 to fix #211

Co-authored-by: Trinkle23897 <463003665@qq.com>
BFAnas pushed a commit to BFAnas/tianshou that referenced this pull request May 5, 2024
* fix thu-ml#203

* no_grad argument in collector.collect
BFAnas pushed a commit to BFAnas/tianshou that referenced this pull request May 5, 2024
- replace DiagGuassian with Independent(Normal) (pytorch has already supported this)
- detach alpha from autograd
- add value/alpha to result (more informational)
- revert thu-ml#204 to fix thu-ml#211

Co-authored-by: Trinkle23897 <463003665@qq.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Why setting policy.train() before collect samples in offline_trainer?
4 participants