try 100M steps on walkerdynamic

Project/Assets/ML-Agents/Examples/Walker/Prefabs/DynamicPlatformWalker.prefab

       propertyPath: m_Name
       value: WalkerRagdoll
       objectReference: {fileID: 0}
+    - target: {fileID: 895268871377934297, guid: 765582efd9dda46ed98564603316353f,
+        type: 3}
+      propertyPath: m_Model
+      value: 
+      objectReference: {fileID: 11400000, guid: 465050f5bacbb4ec285a0d912a0f4f67,
+        type: 3}
     - target: {fileID: 895268871377934298, guid: 765582efd9dda46ed98564603316353f,
         type: 3}
       propertyPath: m_LocalPosition.x

config/trainer_config.yaml

     time_horizon: 1000
     batch_size: 2048
     buffer_size: 20480
-    max_steps: 2e7
+    # max_steps: 2e7
+    max_steps: 1e8
     summary_freq: 30000
     num_layers: 3
     hidden_units: 512

Project/Assets/ML-Agents/Examples/Walker/TFModels/brandonh_2020-05-15_2020-05-15-21-48-18_walkdylist-ppo_results_walkdylist-ppo_WalkerDynamic.nn.meta

+fileFormatVersion: 2
+guid: 465050f5bacbb4ec285a0d912a0f4f67
+ScriptedImporter:
+  fileIDToRecycleName:
+    11400000: main obj
+    11400002: model data
+  externalObjects: {}
+  userData: 
+  assetBundleName: 
+  assetBundleVariant: 
+  script: {fileID: 11500000, guid: 19ed1486aa27d4903b34839f37b8f69f, type: 3}