hiro/ray
1
0
Fork 0
mirror of https://github.com/vale981/ray synced 2025-03-06 10:31:39 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions

[rllib] replace the assertion in SyncReplayOptimizer by a warning (#4534)

Browse source
This commit is contained in:
Jones Wong 2019-04-02 01:43:22 -07:00 • committed by Eric Liang
parent 60b230b8ad
commit fe7763e786
1 changed files with 6 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
python/ray/rllib/optimizers/sync_replay_optimizer.py
View file

@ -2,6 +2,7 @@ from __future__ import absolute_import
from __future__ import division from __future__ import division
from __future__ import print_function from __future__ import print_function
import logging
import collections import collections
import numpy as np import numpy as np
@ -17,6 +18,8 @@ from ray.rllib.utils.compression import pack_if_needed
from ray.rllib.utils.timer import TimerStat from ray.rllib.utils.timer import TimerStat
from ray.rllib.utils.schedules import LinearSchedule from ray.rllib.utils.schedules import LinearSchedule
logger = logging.getLogger(__name__)
class SyncReplayOptimizer(PolicyOptimizer): class SyncReplayOptimizer(PolicyOptimizer):
"""Variant of the local sync optimizer that supports replay (for DQN). """Variant of the local sync optimizer that supports replay (for DQN).
@ -69,7 +72,9 @@ class SyncReplayOptimizer(PolicyOptimizer):
self.replay_buffers = collections.defaultdict(new_buffer) self.replay_buffers = collections.defaultdict(new_buffer)
assert buffer_size >= self.replay_starts if buffer_size < self.replay_starts:
logger.warning("buffer_size={} < replay_starts={}".format(
buffer_size, self.replay_starts))
@override(PolicyOptimizer) @override(PolicyOptimizer)
def step(self): def step(self):