Merge pull request #1419 from Unity-Technologies/develop-multi-delay

Wait between environment launches

ml-agents/mlagents/trainers/learn.py

 
 import logging
 
-import os
-import multiprocessing
+from multiprocessing import Process, Queue
 import numpy as np
 from docopt import docopt
 
 
-def run_training(sub_id, run_seed, run_options):
+def run_training(sub_id, run_seed, run_options, process_queue):
+    :param process_queue: Queue used to send signal back to main.
     :param sub_id: Unique id for training session.
     :param run_seed: Random seed used for training.
     :param run_options: Command line arguments for training.
     no_graphics = run_options['--no-graphics']
     trainer_config_path = run_options['<trainer-config-path>']
 
-    # Create controller and begin training.
+    # Create controller and launch environment.
+
+    # Signal that environment has been launched.
+    process_queue.put(True)
+
+    # Begin training
     tc.start_learning()
 
 
     for i in range(num_runs):
         if seed == -1:
             run_seed = np.random.randint(0, 10000)
-        p = multiprocessing.Process(target=run_training, args=(i, run_seed, options))
+        process_queue = Queue()
+        p = Process(target=run_training, args=(i, run_seed, options, process_queue))
+        # Wait for signal that environment has successfully launched
+        while process_queue.get() is not True:
+            continue