use directory for model overrides instead (#4003)

* use directory for model overrides instead * fix maxEpisodes setting
4 年前 · ef530217
--- a/Project/Assets/ML-Agents/Examples/SharedAssets/Scripts/ModelOverrider.cs
+++ b/Project/Assets/ML-Agents/Examples/SharedAssets/Scripts/ModelOverrider.cs
    public class ModelOverrider : MonoBehaviour
    {
        const string k_CommandLineModelOverrideFlag = "--mlagents-override-model";
+        const string k_CommandLineModelOverrideDirectoryFlag = "--mlagents-override-model-directory";
        const string k_CommandLineQuitAfterEpisodesFlag = "--mlagents-quit-after-episodes";
        const string k_CommandLineQuitOnLoadFailure = "--mlagents-quit-on-load-failure";

        // Assets paths to use, with the behavior name as the key.
        Dictionary<string, string> m_BehaviorNameOverrides = new Dictionary<string, string>();

+        string m_BehaviorNameOverrideDirectory;
+
+

        // Max episodes to run. Only used if > 0
        // Will default to 1 if override models are specified, otherwise 0.
            get { return m_PreviousNumSteps + m_NumSteps; }
        }

+        public bool HasOverrides
+        {
+            get { return m_BehaviorNameOverrides.Count > 0 || !string.IsNullOrEmpty(m_BehaviorNameOverrideDirectory);  }
+        }
+
+        public static string GetOverrideBehaviorName(string originalBehaviorName)
+        {
+            return $"Override_{originalBehaviorName}";
+        }
+
        /// <summary>
        /// Get the asset path to use from the commandline arguments.
        /// </summary>
                    var key = args[i + 1].Trim();
                    var value = args[i + 2].Trim();
                    m_BehaviorNameOverrides[key] = value;
+                }
+                else if (args[i] == k_CommandLineModelOverrideDirectoryFlag && i < args.Length-1)
+                {
+                    m_BehaviorNameOverrideDirectory = args[i + 1].Trim();
                }
                else if (args[i] == k_CommandLineQuitAfterEpisodesFlag && i < args.Length-1)
                {
                }
            }

-            if (m_BehaviorNameOverrides.Count > 0)
+            if (HasOverrides)
            {
                // If overriding models, set maxEpisodes to 1 or the command line value
                m_MaxEpisodes = maxEpisodes > 0 ? maxEpisodes : 1;
            m_Agent = GetComponent<Agent>();

            GetAssetPathFromCommandLine();
-            if (m_BehaviorNameOverrides.Count > 0)
+            if (HasOverrides)
            {
                OverrideModel();
            }
            m_NumSteps++;
        }

-        NNModel GetModelForBehaviorName(string behaviorName)
+        public NNModel GetModelForBehaviorName(string behaviorName)
        {
            if (m_CachedModels.ContainsKey(behaviorName))
            {
-            if (!m_BehaviorNameOverrides.ContainsKey(behaviorName))
+            string assetPath = null;
+            if (m_BehaviorNameOverrides.ContainsKey(behaviorName))
-                Debug.Log($"No override for BehaviorName {behaviorName}");
-                return null;
+                assetPath = m_BehaviorNameOverrides[behaviorName];
+            }
+            else if(!string.IsNullOrEmpty(m_BehaviorNameOverrideDirectory))
+            {
+                assetPath = Path.Combine(m_BehaviorNameOverrideDirectory, $"{behaviorName}.nn");
-            var assetPath = m_BehaviorNameOverrides[behaviorName];
+            if (string.IsNullOrEmpty(assetPath))
+            {
+                Debug.Log($"No override for BehaviorName {behaviorName}, and no directory set.");
+                return null;
+            }

            byte[] model = null;
            try
            catch(IOException)
            {
-                Debug.Log($"Couldn't load file {assetPath}", this);
+                Debug.Log($"Couldn't load file {assetPath} at full path {Path.GetFullPath(assetPath)}", this);
                // Cache the null so we don't repeatedly try to load a missing file
                m_CachedModels[behaviorName] = null;
                return null;
                    $"and that the model file exists"
                );
                Application.Quit(1);
+#if UNITY_EDITOR
+                EditorApplication.isPlaying = false;
+#endif
-            m_Agent.SetModel($"Override_{behaviorName}", nnModel);
+            m_Agent.SetModel(GetOverrideBehaviorName(behaviorName), nnModel);

        }
    }
--- a/Project/Assets/ML-Agents/Examples/Soccer/Prefabs/StrikersVsGoalieField.prefab
+++ b/Project/Assets/ML-Agents/Examples/Soccer/Prefabs/StrikersVsGoalieField.prefab
  - component: {fileID: 114492261207303438}
  - component: {fileID: 114320493772006642}
  - component: {fileID: 9152743230243588598}
+  - component: {fileID: 9171805407464329310}
  m_Layer: 0
  m_Name: PurpleGoalie
  m_TagString: purpleAgent
  m_Name: 
  m_EditorClassIdentifier: 
  m_BrainParameters:
-    vectorObservationSize: 0
-    numStackedVectorObservations: 1
-    vectorActionSize: 030000000300000003000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 0
+    VectorObservationSize: 0
+    NumStackedVectorObservations: 1
+    VectorActionSize: 030000000300000003000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 0
  m_Model: {fileID: 11400000, guid: e9c10c18f4eb745d19186a54dbe3ca2e, type: 3}
  m_InferenceDevice: 0
  m_BehaviorType: 0
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114492261207303438
 MonoBehaviour:
  m_ObjectHideFlags: 0
  agentParameters:
    maxStep: 0
  hasUpgradedFromAgentParameters: 1
-  maxStep: 3000
+  MaxStep: 3000
  team: 0
  area: {fileID: 114559182131992928}
  position: 1
  m_EditorClassIdentifier: 
  DecisionPeriod: 5
  TakeActionsBetweenDecisions: 1
+--- !u!114 &9171805407464329310
+MonoBehaviour:
+  m_ObjectHideFlags: 0
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  m_GameObject: {fileID: 1095606497496374}
+  m_Enabled: 1
+  m_EditorHideFlags: 0
+  m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
+  m_Name: 
+  m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
 --- !u!1 &1100217258374548
 GameObject:
  m_ObjectHideFlags: 0
  - component: {fileID: 114850431417842684}
  - component: {fileID: 114516244030127556}
  - component: {fileID: 404683423509059512}
+  - component: {fileID: 5776656799174978208}
  m_Layer: 0
  m_Name: BlueStriker
  m_TagString: blueAgent
  m_Name: 
  m_EditorClassIdentifier: 
  m_BrainParameters:
-    vectorObservationSize: 0
-    numStackedVectorObservations: 1
-    vectorActionSize: 030000000300000003000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 0
+    VectorObservationSize: 0
+    NumStackedVectorObservations: 1
+    VectorActionSize: 030000000300000003000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 0
  m_Model: {fileID: 11400000, guid: 75a830685bf8e43918adc4783a2abebf, type: 3}
  m_InferenceDevice: 0
  m_BehaviorType: 0
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114850431417842684
 MonoBehaviour:
  m_ObjectHideFlags: 0
  agentParameters:
    maxStep: 0
  hasUpgradedFromAgentParameters: 1
-  maxStep: 3000
+  MaxStep: 3000
  team: 1
  area: {fileID: 114559182131992928}
  position: 0
  m_EditorClassIdentifier: 
  DecisionPeriod: 5
  TakeActionsBetweenDecisions: 1
+--- !u!114 &5776656799174978208
+MonoBehaviour:
+  m_ObjectHideFlags: 0
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  m_GameObject: {fileID: 1131626411948014}
+  m_Enabled: 1
+  m_EditorHideFlags: 0
+  m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
+  m_Name: 
+  m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
 --- !u!1 &1141134673700168
 GameObject:
  m_ObjectHideFlags: 0
  - component: {fileID: 5379409612883756837}
  - component: {fileID: 2562571719799803906}
  - component: {fileID: 1018414316889932458}
+  - component: {fileID: 493348456414434994}
  m_Layer: 0
  m_Name: BlueStriker (1)
  m_TagString: blueAgent
  m_Name: 
  m_EditorClassIdentifier: 
  m_BrainParameters:
-    vectorObservationSize: 0
-    numStackedVectorObservations: 1
-    vectorActionSize: 030000000300000003000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 0
+    VectorObservationSize: 0
+    NumStackedVectorObservations: 1
+    VectorActionSize: 030000000300000003000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 0
  m_Model: {fileID: 11400000, guid: 75a830685bf8e43918adc4783a2abebf, type: 3}
  m_InferenceDevice: 0
  m_BehaviorType: 0
+  m_ObservableAttributeHandling: 0
 --- !u!114 &5379409612883756837
 MonoBehaviour:
  m_ObjectHideFlags: 0
  agentParameters:
    maxStep: 0
  hasUpgradedFromAgentParameters: 1
-  maxStep: 3000
+  MaxStep: 3000
  team: 1
  area: {fileID: 114559182131992928}
  position: 0
  m_EditorClassIdentifier: 
  DecisionPeriod: 5
  TakeActionsBetweenDecisions: 1
+--- !u!114 &493348456414434994
+MonoBehaviour:
+  m_ObjectHideFlags: 0
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  m_GameObject: {fileID: 8360301818957399454}
+  m_Enabled: 1
+  m_EditorHideFlags: 0
+  m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
+  m_Name: 
+  m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
--- a/Project/Assets/ML-Agents/Examples/WallJump/Prefabs/WallJumpArea.prefab
+++ b/Project/Assets/ML-Agents/Examples/WallJump/Prefabs/WallJumpArea.prefab
  m_Name: 
  m_EditorClassIdentifier: 
  m_BrainParameters:
-    vectorObservationSize: 4
-    numStackedVectorObservations: 6
-    vectorActionSize: 03000000030000000300000002000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 0
+    VectorObservationSize: 4
+    NumStackedVectorObservations: 6
+    VectorActionSize: 03000000030000000300000002000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 0
  m_Model: {fileID: 11400000, guid: 0468bf44b1efd4992b6bf22cadb50d89, type: 3}
  m_InferenceDevice: 0
  m_BehaviorType: 0
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114925928594762506
 MonoBehaviour:
  m_ObjectHideFlags: 0
  agentParameters:
    maxStep: 0
  hasUpgradedFromAgentParameters: 1
-  maxStep: 2000
+  MaxStep: 2000
  noWallBrain: {fileID: 11400000, guid: fb2ce36eb40b6480e94ea0b5d7573e47, type: 3}
  smallWallBrain: {fileID: 11400000, guid: fb2ce36eb40b6480e94ea0b5d7573e47, type: 3}
  bigWallBrain: {fileID: 11400000, guid: 0468bf44b1efd4992b6bf22cadb50d89, type: 3}
  m_EditorClassIdentifier: 
  DecisionPeriod: 5
  TakeActionsBetweenDecisions: 1
-  offsetStep: 0
 --- !u!114 &7445449404652947848
 MonoBehaviour:
  m_ObjectHideFlags: 0
  m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
  m_Name: 
  m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
 --- !u!1 &1264699583886832
 GameObject:
  m_ObjectHideFlags: 0
--- a/Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpAgent.cs
+++ b/Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpAgent.cs
 using Unity.MLAgents;
 using Unity.Barracuda;
 using Unity.MLAgents.Sensors;
+using Unity.MLAgentsExamples;

 public class WallJumpAgent : Agent
 {
    Vector3 m_JumpTargetPos;
    Vector3 m_JumpStartingPos;

+    string m_NoWallBehaviorName = "SmallWallJump";
+    string m_SmallWallBehaviorName = "SmallWallJump";
+    string m_BigWallBehaviorName = "BigWallJump";
+
    EnvironmentParameters m_ResetParams;

    public override void Initialize()
        spawnArea.SetActive(false);

        m_ResetParams = Academy.Instance.EnvironmentParameters;
+
+        // Update model references if we're overriding
+        var modelOverrider = GetComponent<ModelOverrider>();
+        if (modelOverrider.HasOverrides)
+        {
+            noWallBrain = modelOverrider.GetModelForBehaviorName(m_NoWallBehaviorName);
+            m_NoWallBehaviorName = ModelOverrider.GetOverrideBehaviorName(m_NoWallBehaviorName);
+
+            smallWallBrain = modelOverrider.GetModelForBehaviorName(m_SmallWallBehaviorName);
+            m_SmallWallBehaviorName = ModelOverrider.GetOverrideBehaviorName(m_SmallWallBehaviorName);
+
+            bigWallBrain = modelOverrider.GetModelForBehaviorName(m_BigWallBehaviorName);
+            m_BigWallBehaviorName = ModelOverrider.GetOverrideBehaviorName(m_BigWallBehaviorName);
+        }
    }

    // Begin the jump sequence
                m_ResetParams.GetWithDefault("no_wall_height", 0),
                localScale.z);
            wall.transform.localScale = localScale;
-            SetModel("SmallWallJump", noWallBrain);
+            SetModel(m_NoWallBehaviorName, noWallBrain);
        }
        else if (config == 1)
        {
                localScale.z);
            wall.transform.localScale = localScale;
-            SetModel("SmallWallJump", smallWallBrain);
+            SetModel(m_SmallWallBehaviorName, smallWallBrain);
        }
        else
        {
                height,
                localScale.z);
            wall.transform.localScale = localScale;
-            SetModel("BigWallJump", bigWallBrain);
+            SetModel(m_BigWallBehaviorName, bigWallBrain);
        }
    }
 }