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
Migrate REINFORCE trainer to Lightning #388
Migrate REINFORCE trainer to Lightning #388
Conversation
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.
|
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
d4ea592
to
5021a0a
Compare
This pull request was exported from Phabricator. Differential Revision: D26246712 |
Summary: Pull Request resolved: facebookresearch#388 I migrated REINFORCE trainer to Lightning. Differential Revision: D26246712 fbshipit-source-id: 5982d9252b6898c721738c674050243ebc15f079
5021a0a
to
77c7f2e
Compare
This pull request was exported from Phabricator. Differential Revision: D26246712 |
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
77c7f2e
to
878099d
Compare
This pull request was exported from Phabricator. Differential Revision: D26246712 |
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
878099d
to
57d3996
Compare
This pull request was exported from Phabricator. Differential Revision: D26246712 |
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
57d3996
to
7090765
Compare
This pull request was exported from Phabricator. Differential Revision: D26246712 |
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
7090765
to
9e09499
Compare
This pull request was exported from Phabricator. Differential Revision: D26246712 |
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
9e09499
to
5f2c628
Compare
This pull request was exported from Phabricator. Differential Revision: D26246712 |
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
5f2c628
to
aab397d
Compare
This pull request was exported from Phabricator. Differential Revision: D26246712 |
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
aab397d
to
e875cdd
Compare
This pull request was exported from Phabricator. Differential Revision: D26246712 |
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
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
643b3c6
to
9d4d7c7
Compare
This pull request was exported from Phabricator. Differential Revision: D26246712 |
This pull request has been merged in 4bbc12f. |
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