Closed hexiang-hu closed 5 years ago
(1) Add train_mode to batch_rl_algorithm (2) Add online_rl_algorithm with online data_collector
Looks good! I'm ready to merge it in after the conflicts have been resolved.
Cool, just resolved the conflicts
Thanks for this great PR!
(1) Add train_mode to batch_rl_algorithm (2) Add online_rl_algorithm with online data_collector