
Robert NishiharaandPhilipp Moritz
0eae917766
[rllib] Clean up evolution strategies example. (#1225)
* Remove ES observation statistics.
* Consolidate policy classes.
* Remove random stream.
* Move rollout function out of policy.
* Consolidate policy initialization.
* Replace act implementation with sess.run.
* Remove tf_utils.
* Remove variable scope.
* Remove unused imports.
* Use regular TF session.
* Use MeanStdFilter.
* Minor.
* Clarify naming.
* Update documentation.
* eps -> episodes
* Report noiseless evaluation runs.
* Clean up naming.
* Update documentation.
* Fix some bugs.
* Make it run on atari.
* Don't add action noise during evaluation runs.
* Add ES to checkpoint/restore test.
* Small cleanups and remove redundant calls to get_weights.
* Remove outdated comment.
2017-11-16 21:58:30 -08:00
..
2017-02-27 21:14:31 -08:00
2017-02-27 21:14:31 -08:00
2017-07-16 22:19:33 -07:00
2017-07-16 22:19:33 -07:00
2017-09-12 23:38:21 -07:00
2017-09-09 10:21:51 -07:00
2017-10-29 11:12:17 -07:00
2017-11-09 17:49:06 -08:00
2017-11-16 21:58:30 -08:00
2017-07-16 22:19:33 -07:00
2017-07-16 22:19:33 -07:00
2017-11-15 17:49:31 -08:00
2017-10-09 22:58:58 -07:00
2017-08-29 21:37:53 -07:00
2017-07-16 22:19:33 -07:00
2017-08-19 17:38:14 -07:00
2017-11-09 17:49:06 -08:00
2017-03-24 17:33:26 -07:00
2017-10-11 23:13:07 -07:00
2017-10-11 23:13:07 -07:00
2017-09-04 22:58:49 -07:00
2017-07-16 22:19:33 -07:00
2017-09-30 09:56:52 -07:00
2017-10-18 11:49:28 -07:00
2017-07-16 22:19:33 -07:00
2017-07-16 22:19:33 -07:00
2017-07-16 22:19:33 -07:00
2017-06-02 20:17:48 +00:00
2017-07-16 22:19:33 -07:00
2017-07-16 22:19:33 -07:00
2017-07-16 22:19:33 -07:00
2017-07-16 22:19:33 -07:00
2017-09-16 15:41:52 -07:00