Migrate REINFORCE trainer to Lightning #388
Closed
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
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
Codecov Report
@@ Coverage Diff @@
## master #388 +/- ##
===========================================
+ Coverage 69.85% 82.23% +12.38%
===========================================
Files 296 305 +9
Lines 16594 17356 +762
Branches 42 42
===========================================
+ Hits 11591 14272 +2681
+ Misses 4979 3060 -1919
Partials 24 24
Continue to review full report at Codecov.
|
alexnikulkov
added a commit
to alexnikulkov/ReAgent
that referenced
this pull request
Feb 5, 2021
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. I don't like the fake optimizer trick and I'll look into doing it more cleanly. Differential Revision: D26246712 fbshipit-source-id: e87d503b1ce6b629016ce629e6f4f4b0511f5b6a
alexnikulkov
force-pushed
the
export-D26246712
branch
from
d4ea592
to
5021a0a
Compare
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
alexnikulkov
added a commit
to alexnikulkov/ReAgent
that referenced
this pull request
Feb 19, 2021
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. Differential Revision: D26246712 fbshipit-source-id: 5982d9252b6898c721738c674050243ebc15f079
alexnikulkov
force-pushed
the
export-D26246712
branch
from
5021a0a
to
77c7f2e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
alexnikulkov
added a commit
to alexnikulkov/ReAgent
that referenced
this pull request
Feb 19, 2021
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. I also added a gym test, based on a new parametric test function which performs online learning without a replay buffer. Differential Revision: D26246712 fbshipit-source-id: 29a0daa0167d9e16f5893c3d3f383c0038287ec6
alexnikulkov
force-pushed
the
export-D26246712
branch
from
77c7f2e
to
878099d
Compare
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
alexnikulkov
added a commit
to alexnikulkov/ReAgent
that referenced
this pull request
Feb 19, 2021
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. I also added a gym test, based on a new parametric test function which performs online learning without a replay buffer. Differential Revision: D26246712 fbshipit-source-id: 369327c001592c5d1cf1eba39a9a51f87d7bb133
alexnikulkov
force-pushed
the
export-D26246712
branch
from
878099d
to
57d3996
Compare
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
alexnikulkov
added a commit
to alexnikulkov/ReAgent
that referenced
this pull request
Feb 19, 2021
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. I also added a gym test, based on a new parametric test function which performs online learning without a replay buffer. Differential Revision: D26246712 fbshipit-source-id: cb292c2ad87356c62b06e4103f3f2c20c1f87512
alexnikulkov
force-pushed
the
export-D26246712
branch
from
57d3996
to
7090765
Compare
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
alexnikulkov
added a commit
to alexnikulkov/ReAgent
that referenced
this pull request
Feb 19, 2021
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. I also added a gym test, based on a new parametric test function which performs online learning without a replay buffer. Reviewed By: kittipatv Differential Revision: D26246712 fbshipit-source-id: 19105e16b07620d746eaa7f89b8ae855b1b174bf
alexnikulkov
force-pushed
the
export-D26246712
branch
from
7090765
to
9e09499
Compare
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
alexnikulkov
added a commit
to alexnikulkov/ReAgent
that referenced
this pull request
Feb 19, 2021
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. I also added a gym test, based on a new parametric test function which performs online learning without a replay buffer. Reviewed By: kittipatv Differential Revision: D26246712 fbshipit-source-id: 13974dab2efad2c837a17a73b4fa69071fcb99d3
alexnikulkov
force-pushed
the
export-D26246712
branch
from
9e09499
to
5f2c628
Compare
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
alexnikulkov
added a commit
to alexnikulkov/ReAgent
that referenced
this pull request
Feb 22, 2021
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. I also added a gym test, based on a new parametric test function which performs online learning without a replay buffer. Reviewed By: kittipatv Differential Revision: D26246712 fbshipit-source-id: 276bf2f81d37045f48e3d8b2799c8800b1e09be3
alexnikulkov
force-pushed
the
export-D26246712
branch
from
5f2c628
to
aab397d
Compare
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
alexnikulkov
added a commit
to alexnikulkov/ReAgent
that referenced
this pull request
Feb 22, 2021
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. I also added a gym test, based on a new parametric test function which performs online learning without a replay buffer. Reviewed By: kittipatv Differential Revision: D26246712 fbshipit-source-id: 0b8e151caf506aaead44a9b048f004016d7d7fc4
alexnikulkov
force-pushed
the
export-D26246712
branch
from
aab397d
to
e875cdd
Compare
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
alexnikulkov
added a commit
to alexnikulkov/ReAgent
that referenced
this pull request
Feb 23, 2021
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. I also added a gym test, based on a new parametric test function which performs online learning without a replay buffer. Reviewed By: kittipatv Differential Revision: D26246712 fbshipit-source-id: 7acd0f8db4b8dcbc1f01454e2543fe6ac8aebe9f
alexnikulkov
force-pushed
the
export-D26246712
branch
from
e875cdd
to
643b3c6
Compare
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
Differential Revision: D26592353 fbshipit-source-id: 8f7039c4bc571097c5d5d8db9a561f1080674d1f
Differential Revision: D26246713 fbshipit-source-id: 0e28902341a9805df7e4ccf073f68d176de43b54
…n_old() method for compatibility with old workflows Differential Revision: D26270800 fbshipit-source-id: 2e79bdd3bddbc3ff1b3811d60f350307ebc6b0a4
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. I also added a gym test, based on a new parametric test function which performs online learning without a replay buffer. Reviewed By: kittipatv Differential Revision: D26246712 fbshipit-source-id: a1afdd6e81613b5cf451f212906d1bf7b056d2e1
alexnikulkov
force-pushed
the
export-D26246712
branch
from
643b3c6
to
9d4d7c7
Compare
|
This pull request was exported from Phabricator. Differential Revision: D26246712 |
|
This pull request has been merged in 4bbc12f. |
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.
Summary: I migrated REINFORCE trainer to Lightning. I don't like the fake optimizer trick and I'll look into doing it more cleanly.
Differential Revision: D26246712