[docs] Add missing config and make sure to use floats in example (#3989)

* Add missing config and make sure to use floats in example

* Moved init_path

docs/Training-ML-Agents.md

   normalize: false
   num_layers: 2
   time_horizon: 64
+  summary_freq: 10000
+  init_path: null
 
   # PPO-specific configs
   beta: 5.0e-3
     batch_size: 512
     num_epoch: 3
     samples_per_update: 0
-    init_path:
 
   reward_signals:
     # environment reward
       strength: 0.02
       gamma: 0.99
       encoding_size: 256
-      learning_rate: 3e-4
+      learning_rate: 3.0e-4
 
     # GAIL
     gail:
       demo_path: Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
-      learning_rate: 3e-4
+      learning_rate: 3.0e-4
       use_actions: false
       use_vail: false