3 Commits

Include renames

Author	SHA1	Message	Date
Eric LiangandPhilipp Moritz	4374ad1453	Policy gradient example: Support multi-GPU training (#584) ... * add tf metrics * comments * fix network scopes * add doc * initial work * try with 3 virtual cpus * clean up metrics * use format string * fix trace level * back to pong * always run summary on cpu * plot intermediate and final sgd stats * add back a global step * update * add timeline * use staging area and reuse weights properly * stage at cpu * whoops, stage only the batch * clean up a bit * fix py flake * wip * create an optimizer graph per device * print timeline on 5th batch instead * print examples per second * log placement for training ops * force placement on cpu:0 * try separating weights onto different gpus * try using nccl * add cpu fallback * remove space from date * check has gpu device * fix flag config * checkpoint * wip * update * add some timing * trace loading * try cpu * revert that * remove expensive test * lint * cleanups * clean up timers * clean it up a bit * fix code for non-scalar action spaces * address some nits * fix quotes * efficient shuffling between sgd epochs	2017-06-13 06:03:25 +00:00
Robert NishiharaandAlexey Tumanov	3ebfd850e1	Make example applications pep8 compliant. (#553) ... * Test examples for pep8 compliance. * Make rl_pong example pep8 compliant. * Make policy gradient example pep8 compliant. * Make lbfgs example pep8 compliant. * Make hyperopt example pep8 compliant. * Make a3c example pep8 compliant. * Make evolution strategies example pep8 compliant. * Make resnet example pep8 compliant. * Fix.	2017-05-16 14:12:18 -07:00
Philipp MoritzandRobert Nishihara	555dcf35a2	Add policy gradient example. (#344) ... * add policy gradient example * fix typos * Minor changes plus some documentation. * Minor fixes.	2017-03-07 23:42:44 -08:00