Merge branch 'master' into multi_gpu_other_algos

rllib/agents/ppo/ppo.py

@@ -21,6 +21,7 @@
 from ray.rllib.execution.train_ops import TrainOneStep, TrainTFMultiGPU
 from ray.rllib.execution.metric_ops import StandardMetricsReporting
 from ray.rllib.policy.policy import LEARNER_STATS_KEY, Policy
+from ray.rllib.policy.sample_batch import DEFAULT_POLICY_ID
 from ray.rllib.utils.typing import TrainerConfigDict
 from ray.util.iter import LocalIterator