test cloud training

ml-agents/mlagents/trainers/learn.py

         run_seed = np.random.randint(0, 10000)
     run_training(run_seed, options)
     if options.behaviors.transfer:
-        os.system('mlagents-learn config/ppo_transfer/3DBallHard.yaml --env=envs/3dballhard --num-envs=4 --force')
+        os.system('mlagents-learn config/ppo_transfer/3DBallHard.yaml --env=/unity-volume/3dballhard --num-envs=4 --force')
 
 
 def main():

config/ppo_transfer/CrawlerStatic.yaml

+behaviors:
+  CrawlerStatic:
+    trainer_type: ppo_transfer
+    hyperparameters:
+      batch_size: 2024
+      buffer_size: 20240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 10000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: true