wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-20 12:40:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

[RLlib] Issue 7401: In eval mode (if evaluation_episodes > 0), agent hangs if Env does not terminate. (#7448)

Browse Source 
* Fix.

* Rollback.

* Fix issue 7421.

* Fix.
This commit is contained in:
Eric Liang
2020-03-04 12:58:34 -08:00
committed by GitHub
parent c38224d8e5
commit fddeb6809c
4 changed files with 17 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rllib/evaluation/sample_batch_builder.py
+2 -2
View File
@@ -95,9 +95,9 @@ class MultiAgentSampleBatchBuilder:
def total(self):
"""Returns summed number of steps across all agent buffers."""
return sum(p.count for p in self.policy_builders.values())
return sum(a.count for a in self.agent_builders.values())
def has_pending_data(self):
def has_pending_agent_data(self):
"""Returns whether there is pending unprocessed data."""
return len(self.agent_builders) > 0