Avoid stall when multiple brains are present

ml-agents/mlagents/trainers/trainer/rl_trainer.py

 from typing import Dict, List
 from collections import defaultdict
 import abc
+import time
 
 from mlagents.trainers.optimizer.tf_optimizer import TFOptimizer
 from mlagents.trainers.buffer import AgentBuffer
                 # We grab at most the maximum length of the queue.
                 # This ensures that even if the queue is being filled faster than it is
                 # being emptied, the trajectories in the queue are on-policy.
+                _queried = False
+                    _queried = True
+                if self.threaded and not _queried:
+                    # Avoid busy-waiting
+                    time.sleep(0.05)
         if self.should_still_train:
             if self._is_ready_update():
                 with hierarchical_timer("_update_policy"):