gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-04-17 04:53:30 +02:00
Code Issues Projects Releases Wiki Activity

bug fixes for OPE (#311)

Browse Source
This commit is contained in:
Gal Leibovich
2019-05-21 16:39:11 +03:00
committed by GitHub
parent 85d70dd7d5
commit acceb03ac0
8 changed files with 38 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
rl_coach/memories/non_episodic/experience_replay.py
View File

@@ -92,7 +92,7 @@ class ExperienceReplay(Memory):
self.reader_writer_lock.release_writing()
return batch
def get_shuffled_data_generator(self, size: int) -> List[Transition]:
def get_shuffled_training_data_generator(self, size: int) -> List[Transition]:
"""
Get an generator for iterating through the shuffled replay buffer, for processing the data in epochs.
If the requested size is larger than the number of samples available in the replay buffer then the batch will