3 commits

Author	SHA1	Message	Date
Eric Liang	7501ee51db	[rllib] Rename PolicyEvaluator => RolloutWorker (#4820)	2019-06-03 06:49:24 +08:00
Eric Liang	37208216ae	[rllib] Rename Agent to Trainer (#4556)	2019-04-07 00:36:18 -07:00
Eric Liang	995ac24a2c	[rllib] clarify train batch size for PPO (#2793) ... It's possible to configure PPO in a way that ends up discarding most of the samples (they are treated as "stragglers"). Add a warning when this happens, and raise an exception if the waste is particularly egregious.	2018-09-05 12:06:13 -07:00