Refactored GridWorld (#225)

Greatly simplified GridWorld code. It now also only uses a visual observation rather than state vector in order to demonstrate learning purely from a visual input.
7 年前 · 00534390
--- a/docs/Example-Environments.md
+++ b/docs/Example-Environments.md
    * +1.0 if the agent navigates to the goal position of the grid (episode ends).
    * -1.0 if the agent navigates to an obstacle (episode ends).
 * Brains: One brain with the following state/action space.
-    * State space: (Continuous) 6 variables corresponding to position of agent and nearest goal and obstacle.
+    * State space: None
    * Action space: (Discrete) Size of 4, corresponding to movement in cardinal directions.
    * Observations: One corresponding to top-down view of GridWorld.
 * Reset Parameters: Three, corresponding to grid size, number of obstacles, and number of goals.
--- a/python/ppo/models.py
+++ b/python/ppo/models.py
        self.advantage = tf.placeholder(shape=[None, 1], dtype=tf.float32, name='advantages')

        decay_epsilon = tf.train.polynomial_decay(epsilon, self.global_step,
-                                                  max_step, 1e-2,
+                                                  max_step, 0.1,
                                                  power=1.0)

        r_theta = probs / (old_probs + 1e-10)
        decay_beta = tf.train.polynomial_decay(beta, self.global_step,
                                               max_step, 1e-5,
                                               power=1.0)
-        self.loss = self.policy_loss + self.value_loss - decay_beta * tf.reduce_mean(entropy)
+        self.loss = self.policy_loss + 0.5 * self.value_loss - decay_beta * tf.reduce_mean(entropy)

        self.learning_rate = tf.train.polynomial_decay(lr, self.global_step,
                                                       max_step, 1e-10,
--- a/python/unityagents/environment.py
+++ b/python/unityagents/environment.py
                                                             for k in self._resetParameters])) + '\n' + \
               '\n'.join([str(self._brains[b]) for b in self._brains])

-
    def _recv_bytes(self):
        try:
            s = self._conn.recv(self._buffer_size)
--- a/unity-environment/Assets/ML-Agents/Examples/GridWorld/GridWorld.unity
+++ b/unity-environment/Assets/ML-Agents/Examples/GridWorld/GridWorld.unity
    m_PVRDirectSampleCount: 32
    m_PVRSampleCount: 500
    m_PVRBounces: 2
-    m_PVRFiltering: 0
+    m_PVRFilterTypeDirect: 0
+    m_PVRFilterTypeIndirect: 0
+    m_PVRFilterTypeAO: 0
-    m_PVRFilteringAtrousColorSigma: 1
-    m_PVRFilteringAtrousNormalSigma: 1
-    m_PVRFilteringAtrousPositionSigma: 1
+    m_PVRFilteringAtrousPositionSigmaDirect: 0.5
+    m_PVRFilteringAtrousPositionSigmaIndirect: 2
+    m_PVRFilteringAtrousPositionSigmaAO: 1
+    m_ShowResolutionOverlay: 1
  m_LightingDataAsset: {fileID: 0}
  m_UseShadowmask: 0
 --- !u!196 &4
    manualTileSize: 0
    tileSize: 256
    accuratePlacement: 0
+    debug:
+      m_Flags: 0
  m_NavMeshData: {fileID: 0}
 --- !u!1 &2047662
 GameObject:
  m_EditorClassIdentifier: 
  maxSteps: 0
  frameToSkip: 0
-  waitTime: 0.3
+  waitTime: 0
+  isInference: 0
-    width: 80
-    height: 80
-    qualityLevel: 1
-    timeScale: 100
-    targetFrameRate: 60
+    width: 300
+    height: 300
+    qualityLevel: 0
+    timeScale: 10
+    targetFrameRate: -1
  inferenceConfiguration:
    width: 1280
    height: 720
  defaultResetParameters:
  - key: gridSize
-    value: 5
+    value: 3
  - key: numObstacles
    value: 1
  - key: numGoals
  currentStep: 0
-  isInference: 0
-  windowResize: 1
-  trueAgent: {fileID: 0}
-  visualAgent: {fileID: 0}
+  trueAgent: {fileID: 2008405822}
+  gridSize: 0
+  camObject: {fileID: 231883441}
 --- !u!4 &2047664
 Transform:
  m_ObjectHideFlags: 0
  m_Children:
  - {fileID: 1535917238}
  m_Father: {fileID: 0}
-  m_RootOrder: 7
+  m_RootOrder: 6
  m_LocalEulerAnglesHint: {x: 0, y: 0, z: 0}
 --- !u!1 &87755817
 GameObject:
  m_Father: {fileID: 0}
  m_RootOrder: 1
  m_LocalEulerAnglesHint: {x: 90, y: 0, z: 0}
--- !u!114 &201074924
+--- !u!114 &183002472
 MonoBehaviour:
  m_ObjectHideFlags: 0
  m_PrefabParentObject: {fileID: 0}
  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 943466ab374444748a364f9d6c3e2fe2, type: 3}
-  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
+  m_Script: {fileID: 11500000, guid: 41e9bda8f3cf1492fa74926a530f6f70, type: 3}
+  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
-  brain: {fileID: 0}
+  broadcast: 1
+  continuousPlayerActions: []
+  discretePlayerActions:
+  - key: 273
+    value: 0
+  - key: 274
+    value: 1
+  - key: 276
+    value: 2
+  - key: 275
+    value: 3
+  defaultAction: -1
+  brain: {fileID: 1535917239}
 --- !u!1 &231883441
 GameObject:
  m_ObjectHideFlags: 0
  m_Icon: {fileID: 0}
  m_NavMeshLayer: 0
  m_StaticEditorFlags: 0
-  m_IsActive: 1
+  m_IsActive: 0
 --- !u!124 &231883444
 Behaviour:
  m_ObjectHideFlags: 0
  m_TargetEye: 3
  m_HDR: 0
  m_AllowMSAA: 1
+  m_AllowDynamicResolution: 0
-  m_StereoMirrorMode: 0
 --- !u!4 &231883447
 Transform:
  m_ObjectHideFlags: 0
  m_TargetEye: 3
  m_HDR: 0
  m_AllowMSAA: 1
+  m_AllowDynamicResolution: 0
-  m_StereoMirrorMode: 0
--- !u!114 &594701073
+--- !u!114 &651992469
 MonoBehaviour:
  m_ObjectHideFlags: 0
  m_PrefabParentObject: {fileID: 0}
  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 41e9bda8f3cf1492fa74926a530f6f70, type: 3}
-  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
+  m_Script: {fileID: 11500000, guid: 35813a1be64e144f887d7d5f15b963fa, type: 3}
+  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
-  continuousPlayerActions: []
-  discretePlayerActions:
-  - key: 273
-    value: 0
-  - key: 274
-    value: 1
-  - key: 276
-    value: 2
-  - key: 275
-    value: 3
-  defaultAction: -1
  brain: {fileID: 1535917239}
 --- !u!1 &742849316
 GameObject:
  m_Enabled: 1
  m_CastShadows: 0
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Father: {fileID: 486401524}
  m_RootOrder: 2
  m_LocalEulerAnglesHint: {x: 0, y: 0, z: 0}
--- !u!114 &980448580
-MonoBehaviour:
-  m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  m_GameObject: {fileID: 0}
-  m_Enabled: 1
-  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 35813a1be64e144f887d7d5f15b963fa, type: 3}
-  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
-  m_EditorClassIdentifier: 
-  brain: {fileID: 1535917239}
 --- !u!1 &1045409640
 GameObject:
  m_ObjectHideFlags: 0
  m_Enabled: 1
  m_CastShadows: 0
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Father: {fileID: 486401524}
  m_RootOrder: 1
  m_LocalEulerAnglesHint: {x: 0, y: 0, z: 0}
+--- !u!114 &1104052206
+MonoBehaviour:
+  m_ObjectHideFlags: 0
+  m_PrefabParentObject: {fileID: 0}
+  m_PrefabInternal: {fileID: 0}
+  m_GameObject: {fileID: 0}
+  m_Enabled: 1
+  m_EditorHideFlags: 0
+  m_Script: {fileID: 11500000, guid: 943466ab374444748a364f9d6c3e2fe2, type: 3}
+  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
+  m_EditorClassIdentifier: 
+  broadcast: 1
+  brain: {fileID: 1535917239}
 --- !u!1 &1208586857
 GameObject:
  m_ObjectHideFlags: 0
  m_Enabled: 1
  m_CastShadows: 0
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Material: {fileID: 0}
  m_IsTrigger: 0
  m_Enabled: 0
-  serializedVersion: 2
+  serializedVersion: 3
-  m_InflateMesh: 0
+  m_CookingOptions: 14
  m_SkinWidth: 0.01
  m_Mesh: {fileID: 10209, guid: 0000000000000000e000000000000000, type: 0}
 --- !u!33 &1208586860
  m_Name: 
  m_EditorClassIdentifier: 
  brainParameters:
-    stateSize: 6
+    stateSize: 0
-    - width: 32
-      height: 32
-      blackAndWhite: 1
+    - width: 84
+      height: 84
+      blackAndWhite: 0
    actionDescriptions:
    - Up
    - Down
    stateSpaceType: 1
  brainType: 0
  CoreBrains:
-  - {fileID: 594701073}
-  - {fileID: 201074924}
-  - {fileID: 980448580}
-  - {fileID: 1740992925}
-  instanceID: 12718
+  - {fileID: 183002472}
+  - {fileID: 1104052206}
+  - {fileID: 651992469}
+  - {fileID: 1737050307}
+  instanceID: 12658
 --- !u!1 &1553342942
 GameObject:
  m_ObjectHideFlags: 0
  m_PrefabParentObject: {fileID: 0}
  m_PrefabInternal: {fileID: 0}
  m_GameObject: {fileID: 1553342942}
--- !u!1 &1585576318
-GameObject:
-  m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  serializedVersion: 5
-  m_Component:
-  - component: {fileID: 1585576319}
-  - component: {fileID: 1585576320}
-  m_Layer: 0
-  m_Name: trueAgent
-  m_TagString: Untagged
-  m_Icon: {fileID: 0}
-  m_NavMeshLayer: 0
-  m_StaticEditorFlags: 0
-  m_IsActive: 1
--- !u!4 &1585576319
-Transform:
-  m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  m_GameObject: {fileID: 1585576318}
-  m_LocalRotation: {x: 0.04613505, y: -0, z: -0, w: 0.9989352}
-  m_LocalPosition: {x: 0, y: 0, z: 0}
-  m_LocalScale: {x: 1, y: 1, z: 1}
-  m_Children: []
-  m_Father: {fileID: 0}
-  m_RootOrder: 6
-  m_LocalEulerAnglesHint: {x: 0, y: 0, z: 0}
--- !u!114 &1585576320
-MonoBehaviour:
-  m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  m_GameObject: {fileID: 1585576318}
-  m_Enabled: 1
-  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 857707f3f352541d5b858efca4479b95, type: 3}
-  m_Name: 
-  m_EditorClassIdentifier: 
-  brain: {fileID: 1535917239}
-  observations:
-  - {fileID: 489340228}
-  maxStep: 100
-  resetOnDone: 1
-  reward: 0
-  done: 0
-  value: 0
-  CummulativeReward: 0
-  stepCounter: 0
-  agentStoredAction: []
-  memory: []
-  id: 0
-  academy: {fileID: 2047663}
-  gridSize: 0
 --- !u!1 &1726089810
 GameObject:
  m_ObjectHideFlags: 0
  m_Enabled: 1
  m_CastShadows: 0
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Father: {fileID: 486401524}
  m_RootOrder: 4
  m_LocalEulerAnglesHint: {x: 0, y: 90, z: 0}
--- !u!114 &1740992925
+--- !u!114 &1737050307
 MonoBehaviour:
  m_ObjectHideFlags: 0
  m_PrefabParentObject: {fileID: 0}
  m_EditorHideFlags: 0
  m_Script: {fileID: 11500000, guid: 8b23992c8eb17439887f5e944bf04a40, type: 3}
-  m_Name: (Clone)
+  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
-  graphModel: {fileID: 4900000, guid: 9c75cb395cc9943838c0694ad4bc2604, type: 3}
+  broadcast: 0
+  graphModel: {fileID: 4900000, guid: 426162c47484e466d8378d2321a5617c, type: 3}
  graphScope: 
  graphPlaceholders: []
  BatchSizePlaceholderName: batch_size
  m_Enabled: 1
  m_CastShadows: 0
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Father: {fileID: 486401524}
  m_RootOrder: 3
  m_LocalEulerAnglesHint: {x: 0, y: 90, z: 0}
+--- !u!1001 &2008405821
+Prefab:
+  m_ObjectHideFlags: 0
+  serializedVersion: 2
+  m_Modification:
+    m_TransformParent: {fileID: 0}
+    m_Modifications:
+    - target: {fileID: 4587181662868872, guid: 628960e910f094ad1909ecc88cc8016d, type: 2}
+      propertyPath: m_LocalPosition.x
+      value: 0
+      objectReference: {fileID: 0}
+    - target: {fileID: 4587181662868872, guid: 628960e910f094ad1909ecc88cc8016d, type: 2}
+      propertyPath: m_LocalPosition.y
+      value: 0
+      objectReference: {fileID: 0}
+    - target: {fileID: 4587181662868872, guid: 628960e910f094ad1909ecc88cc8016d, type: 2}
+      propertyPath: m_LocalPosition.z
+      value: 0
+      objectReference: {fileID: 0}
+    - target: {fileID: 4587181662868872, guid: 628960e910f094ad1909ecc88cc8016d, type: 2}
+      propertyPath: m_LocalRotation.x
+      value: 0
+      objectReference: {fileID: 0}
+    - target: {fileID: 4587181662868872, guid: 628960e910f094ad1909ecc88cc8016d, type: 2}
+      propertyPath: m_LocalRotation.y
+      value: 0
+      objectReference: {fileID: 0}
+    - target: {fileID: 4587181662868872, guid: 628960e910f094ad1909ecc88cc8016d, type: 2}
+      propertyPath: m_LocalRotation.z
+      value: 0
+      objectReference: {fileID: 0}
+    - target: {fileID: 4587181662868872, guid: 628960e910f094ad1909ecc88cc8016d, type: 2}
+      propertyPath: m_LocalRotation.w
+      value: 1
+      objectReference: {fileID: 0}
+    - target: {fileID: 4587181662868872, guid: 628960e910f094ad1909ecc88cc8016d, type: 2}
+      propertyPath: m_RootOrder
+      value: 7
+      objectReference: {fileID: 0}
+    - target: {fileID: 114841131957396212, guid: 628960e910f094ad1909ecc88cc8016d,
+        type: 2}
+      propertyPath: brain
+      value: 
+      objectReference: {fileID: 1535917239}
+    - target: {fileID: 114841131957396212, guid: 628960e910f094ad1909ecc88cc8016d,
+        type: 2}
+      propertyPath: observations.Array.data[0]
+      value: 
+      objectReference: {fileID: 489340228}
+    - target: {fileID: 114841131957396212, guid: 628960e910f094ad1909ecc88cc8016d,
+        type: 2}
+      propertyPath: academy
+      value: 
+      objectReference: {fileID: 2047663}
+    - target: {fileID: 1657514749044530, guid: 628960e910f094ad1909ecc88cc8016d, type: 2}
+      propertyPath: m_Name
+      value: trueAgent
+      objectReference: {fileID: 0}
+    - target: {fileID: 54942316128460260, guid: 628960e910f094ad1909ecc88cc8016d,
+        type: 2}
+      propertyPath: m_Constraints
+      value: 126
+      objectReference: {fileID: 0}
+    m_RemovedComponents:
+    - {fileID: 114841131957396212, guid: 628960e910f094ad1909ecc88cc8016d, type: 2}
+  m_ParentPrefab: {fileID: 100100000, guid: 628960e910f094ad1909ecc88cc8016d, type: 2}
+  m_IsPrefabParent: 0
+--- !u!1 &2008405822 stripped
+GameObject:
+  m_PrefabParentObject: {fileID: 1657514749044530, guid: 628960e910f094ad1909ecc88cc8016d,
+    type: 2}
+  m_PrefabInternal: {fileID: 2008405821}
+--- !u!114 &2008405823
+MonoBehaviour:
+  m_ObjectHideFlags: 0
+  m_PrefabParentObject: {fileID: 0}
+  m_PrefabInternal: {fileID: 0}
+  m_GameObject: {fileID: 2008405822}
+  m_Enabled: 1
+  m_EditorHideFlags: 0
+  m_Script: {fileID: 11500000, guid: 857707f3f352541d5b858efca4479b95, type: 3}
+  m_Name: 
+  m_EditorClassIdentifier: 
+  brain: {fileID: 1535917239}
+  observations:
+  - {fileID: 489340228}
+  maxStep: 100
+  resetOnDone: 1
+  state: []
+  reward: 0
+  done: 0
+  value: 0
+  CumulativeReward: 0
+  stepCounter: 0
+  agentStoredAction: []
+  memory: []
+  id: 0
+  academy: {fileID: 2047663}
--- a/unity-environment/Assets/ML-Agents/Examples/GridWorld/Resources/agent.prefab
+++ b/unity-environment/Assets/ML-Agents/Examples/GridWorld/Resources/agent.prefab
  - component: {fileID: 4587181662868872}
  - component: {fileID: 33731433020831250}
  - component: {fileID: 65005393801495654}
+  - component: {fileID: 114841131957396212}
+  - component: {fileID: 54942316128460260}
  m_Layer: 8
  m_Name: agent
  m_TagString: agent
  m_Enabled: 1
  m_CastShadows: 1
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Enabled: 1
  m_CastShadows: 1
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Enabled: 1
  m_CastShadows: 0
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Enabled: 1
  m_CastShadows: 1
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_PrefabInternal: {fileID: 100100000}
  m_GameObject: {fileID: 1124730825420414}
  m_Mesh: {fileID: 10202, guid: 0000000000000000e000000000000000, type: 0}
+--- !u!54 &54942316128460260
+Rigidbody:
+  m_ObjectHideFlags: 1
+  m_PrefabParentObject: {fileID: 0}
+  m_PrefabInternal: {fileID: 100100000}
+  m_GameObject: {fileID: 1657514749044530}
+  serializedVersion: 2
+  m_Mass: 1
+  m_Drag: 0
+  m_AngularDrag: 0.05
+  m_UseGravity: 0
+  m_IsKinematic: 0
+  m_Interpolate: 0
+  m_Constraints: 0
+  m_CollisionDetection: 0
 --- !u!65 &65005393801495654
 BoxCollider:
  m_ObjectHideFlags: 1
  serializedVersion: 2
  m_Size: {x: 1, y: 1, z: 1}
  m_Center: {x: 0, y: 0, z: 0}
+--- !u!114 &114841131957396212
+MonoBehaviour:
+  m_ObjectHideFlags: 1
+  m_PrefabParentObject: {fileID: 0}
+  m_PrefabInternal: {fileID: 100100000}
+  m_GameObject: {fileID: 1657514749044530}
+  m_Enabled: 1
+  m_EditorHideFlags: 0
+  m_Script: {fileID: 11500000, guid: 857707f3f352541d5b858efca4479b95, type: 3}
+  m_Name: 
+  m_EditorClassIdentifier: 
+  brain: {fileID: 0}
+  observations:
+  - {fileID: 0}
+  maxStep: 100
+  resetOnDone: 1
+  state: []
+  reward: 0
+  done: 0
+  value: 0
+  CumulativeReward: 0
+  stepCounter: 0
+  agentStoredAction: []
+  memory: []
+  id: 0
+  academy: {fileID: 0}
--- a/unity-environment/Assets/ML-Agents/Examples/GridWorld/Resources/goal.prefab
+++ b/unity-environment/Assets/ML-Agents/Examples/GridWorld/Resources/goal.prefab
  m_Enabled: 1
  m_CastShadows: 1
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Enabled: 1
  m_CastShadows: 1
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Enabled: 0
  m_CastShadows: 0
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_PrefabInternal: {fileID: 100100000}
  m_GameObject: {fileID: 1508142483324970}
  m_Material: {fileID: 0}
-  m_IsTrigger: 0
+  m_IsTrigger: 1
-  m_Size: {x: 1, y: 10, z: 1}
+  m_Size: {x: 0.9, y: 0.9, z: 0.9}
  m_Center: {x: 0, y: 0, z: 0}
 --- !u!65 &65991532807116388
 BoxCollider:
--- a/unity-environment/Assets/ML-Agents/Examples/GridWorld/Resources/pit.prefab
+++ b/unity-environment/Assets/ML-Agents/Examples/GridWorld/Resources/pit.prefab
  m_Enabled: 1
  m_CastShadows: 1
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Enabled: 0
  m_CastShadows: 0
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_Enabled: 1
  m_CastShadows: 1
  m_ReceiveShadows: 1
+  m_DynamicOccludee: 1
  m_MotionVectors: 1
  m_LightProbeUsage: 1
  m_ReflectionProbeUsage: 1
  m_PreserveUVs: 1
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
+  m_StitchLightmapSeams: 0
  m_SelectedEditorRenderState: 3
  m_MinimumChartSize: 4
  m_AutoUVMaxDistance: 0.5
  m_PrefabInternal: {fileID: 100100000}
  m_GameObject: {fileID: 1811317785436014}
  m_Material: {fileID: 0}
-  m_IsTrigger: 0
+  m_IsTrigger: 1
-  m_Size: {x: 1, y: 1, z: 1}
+  m_Size: {x: 0.9, y: 0.9, z: 0.9}
  m_Center: {x: 0, y: 0, z: 0}
 --- !u!65 &65439704505015706
 BoxCollider:
--- a/unity-environment/Assets/ML-Agents/Examples/GridWorld/Scripts/GridAcademy.cs
+++ b/unity-environment/Assets/ML-Agents/Examples/GridWorld/Scripts/GridAcademy.cs
    public List<GameObject> actorObjs;
    [HideInInspector]
    public string[] players;
-    [HideInInspector]
+
-    [HideInInspector]
-    public GameObject visualAgent;
+
+    public int gridSize;
+
+    public GameObject camObject;
+    Camera cam;
-
+        gridSize = (int)resetParameters["gridSize"];
+        cam = camObject.GetComponent<Camera>();
-        trueAgent = GameObject.Find("trueAgent");
+        cam.transform.position = new Vector3(-((int)resetParameters["gridSize"] - 1) / 2f, (int)resetParameters["gridSize"] * 1.25f, -((int)resetParameters["gridSize"] - 1) / 2f);
+        cam.orthographicSize = ((int)resetParameters["gridSize"] + 5f) / 2f;
+
        List<string> playersList = new List<string>();
        actorObjs = new List<GameObject>();
        for (int i = 0; i < (int)resetParameters["numObstacles"]; i++)
-        playersList.Add("agent");

        for (int i = 0; i < (int)resetParameters["numGoals"]; i++)
        {
-        Camera cam = GameObject.Find("Main Camera").GetComponent<Camera>();
-
-        cam.transform.position = new Vector3(-((int)resetParameters["gridSize"] - 1) / 2f, (int)resetParameters["gridSize"] * 1.25f, -((int)resetParameters["gridSize"] - 1) / 2f);
-        cam.orthographicSize = ((int)resetParameters["gridSize"] + 5f) / 2f;
-        GameObject.Find("Plane").transform.localScale = new Vector3((int)resetParameters["gridSize"] / 10.0f, 1f, (int)resetParameters["gridSize"] / 10.0f);
-        GameObject.Find("Plane").transform.position = new Vector3(((int)resetParameters["gridSize"] - 1) / 2f, -0.5f, ((int)resetParameters["gridSize"] - 1) / 2f);
-        GameObject.Find("sN").transform.localScale = new Vector3(1, 1, (int)resetParameters["gridSize"] + 2);
-        GameObject.Find("sS").transform.localScale = new Vector3(1, 1, (int)resetParameters["gridSize"] + 2);
-        GameObject.Find("sN").transform.position = new Vector3(((int)resetParameters["gridSize"] - 1) / 2f, 0.0f, (int)resetParameters["gridSize"]);
-        GameObject.Find("sS").transform.position = new Vector3(((int)resetParameters["gridSize"] - 1) / 2f, 0.0f, -1);
-        GameObject.Find("sE").transform.localScale = new Vector3(1, 1, (int)resetParameters["gridSize"] + 2);
-        GameObject.Find("sW").transform.localScale = new Vector3(1, 1, (int)resetParameters["gridSize"] + 2);
-        GameObject.Find("sE").transform.position = new Vector3((int)resetParameters["gridSize"], 0.0f, ((int)resetParameters["gridSize"] - 1) / 2f);
-        GameObject.Find("sW").transform.position = new Vector3(-1, 0.0f, ((int)resetParameters["gridSize"] - 1) / 2f);
+        GameObject.Find("Plane").transform.localScale = new Vector3(gridSize / 10.0f, 1f, gridSize / 10.0f);
+        GameObject.Find("Plane").transform.position = new Vector3((gridSize - 1) / 2f, -0.5f, (gridSize - 1) / 2f);
+        GameObject.Find("sN").transform.localScale = new Vector3(1, 1, gridSize + 2);
+        GameObject.Find("sS").transform.localScale = new Vector3(1, 1, gridSize + 2);
+        GameObject.Find("sN").transform.position = new Vector3((gridSize - 1) / 2f, 0.0f, gridSize);
+        GameObject.Find("sS").transform.position = new Vector3((gridSize - 1) / 2f, 0.0f, -1);
+        GameObject.Find("sE").transform.localScale = new Vector3(1, 1, gridSize + 2);
+        GameObject.Find("sW").transform.localScale = new Vector3(1, 1, gridSize + 2);
+        GameObject.Find("sE").transform.position = new Vector3(gridSize, 0.0f, (gridSize - 1) / 2f);
+        GameObject.Find("sW").transform.position = new Vector3(-1, 0.0f, (gridSize - 1) / 2f);
-        aCam.orthographicSize = ((int)resetParameters["gridSize"]) / 2f;
-        aCam.transform.position = new Vector3(((int)resetParameters["gridSize"] - 1) / 2f, (int)resetParameters["gridSize"] + 1f, ((int)resetParameters["gridSize"] - 1) / 2f);
+        aCam.orthographicSize = (gridSize) / 2f;
+        aCam.transform.position = new Vector3((gridSize - 1) / 2f, gridSize + 1f, (gridSize - 1) / 2f);

    }

        actorObjs = new List<GameObject>();

        HashSet<int> numbers = new HashSet<int>();
-        while (numbers.Count < players.Length)
+        while (numbers.Count < players.Length + 1)
-            numbers.Add(Random.Range(0, (int)resetParameters["gridSize"] * (int)resetParameters["gridSize"]));
+            numbers.Add(Random.Range(0, gridSize * gridSize));
-            int x = (numbersA[i]) / (int)resetParameters["gridSize"];
-            int y = (numbersA[i]) % (int)resetParameters["gridSize"];
+            int x = (numbersA[i]) / gridSize;
+            int y = (numbersA[i]) % gridSize;
-            if (players[i] == "agent")
-            {
-                trueAgent.transform.position = actorObj.transform.position;
-                trueAgent.transform.rotation = actorObj.transform.rotation;
-                visualAgent = actorObj;
-            }
+
+        int x_a = (numbersA[players.Length]) / gridSize;
+        int y_a = (numbersA[players.Length]) % gridSize;
+        trueAgent.transform.position = new Vector3(x_a, -0.25f, y_a);

    }

--- a/unity-environment/Assets/ML-Agents/Examples/GridWorld/Scripts/GridAgent.cs
+++ b/unity-environment/Assets/ML-Agents/Examples/GridWorld/Scripts/GridAgent.cs
 {
    [Header("Specific to GridWorld")]
    public GridAcademy academy;
-    [HideInInspector]
-    public int gridSize;
-
-    GameObject trueAgent;
-        trueAgent = gameObject;
-        gridSize = (int)academy.resetParameters["gridSize"];
+
-        int closestGoalDistance = 2 * (int)academy.resetParameters["gridSize"];
-        GameObject currentClosestGoal = academy.actorObjs[0];
-        int closestPitDistance = 2 * (int)academy.resetParameters["gridSize"];
-        GameObject currentClosestPit = academy.actorObjs[0];
-        GameObject agent = academy.actorObjs[0];
-        foreach (GameObject actor in academy.actorObjs)
-        {
-            if (actor.CompareTag("agent"))
-            {
-                agent = actor;
-                state.Add(actor.transform.position.x / (gridSize + 1));
-                state.Add(actor.transform.position.z / (gridSize + 1));
-                continue;
-            }
-        }
-        foreach (GameObject actor in academy.actorObjs)
-        {
-            if (actor.CompareTag("goal"))
-            {
-                int distance = (int)Mathf.Abs(agent.transform.position.x - actor.transform.position.x) + (int)Mathf.Abs(agent.transform.position.z - actor.transform.position.z);
-                if (closestGoalDistance > distance)
-                {
-                    closestGoalDistance = distance;
-                    currentClosestGoal = actor;
-                }
-            }
-            if (actor.CompareTag("pit"))
-            {
-                int distance = (int)Mathf.Abs(agent.transform.position.x - actor.transform.position.x) + (int)Mathf.Abs(agent.transform.position.z - actor.transform.position.z);
-                if (closestPitDistance > distance)
-                {
-                    closestPitDistance = distance;
-                    currentClosestPit = actor;
-                }
-            }
-        }
-
-        state.Add(currentClosestGoal.transform.position.x / (gridSize + 1));
-        state.Add(currentClosestGoal.transform.position.z / (gridSize + 1));
-        state.Add(currentClosestPit.transform.position.x / (gridSize + 1));
-        state.Add(currentClosestPit.transform.position.z / (gridSize + 1));
-
        return state;
    }

        int action = Mathf.FloorToInt(act[0]);

        // 0 - Forward, 1 - Backward, 2 - Left, 3 - Right
+        Vector3 targetPos = transform.position;
-            Collider[] blockTest = Physics.OverlapBox(new Vector3(trueAgent.transform.position.x + 1, 0, trueAgent.transform.position.z), new Vector3(0.3f, 0.3f, 0.3f));
-            if (blockTest.Where(col => col.gameObject.tag == "wall").ToArray().Length == 0)
-            {
-                trueAgent.transform.position = new Vector3(trueAgent.transform.position.x + 1, 0, trueAgent.transform.position.z);
-            }
+            targetPos = transform.position + new Vector3(1f, 0, 0f);
-            Collider[] blockTest = Physics.OverlapBox(new Vector3(trueAgent.transform.position.x - 1, 0, trueAgent.transform.position.z), new Vector3(0.3f, 0.3f, 0.3f));
-            if (blockTest.Where(col => col.gameObject.tag == "wall").ToArray().Length == 0)
-            {
-                trueAgent.transform.position = new Vector3(trueAgent.transform.position.x - 1, 0, trueAgent.transform.position.z);
-            }
+            targetPos = transform.position + new Vector3(-1f, 0, 0f);
-            Collider[] blockTest = Physics.OverlapBox(new Vector3(trueAgent.transform.position.x, 0, trueAgent.transform.position.z + 1), new Vector3(0.3f, 0.3f, 0.3f));
-            if (blockTest.Where(col => col.gameObject.tag == "wall").ToArray().Length == 0)
-            {
-                trueAgent.transform.position = new Vector3(trueAgent.transform.position.x, 0, trueAgent.transform.position.z + 1);
-            }
+            targetPos = transform.position + new Vector3(0f, 0, 1f);
-            Collider[] blockTest = Physics.OverlapBox(new Vector3(trueAgent.transform.position.x, 0, trueAgent.transform.position.z - 1), new Vector3(0.3f, 0.3f, 0.3f));
-            if (blockTest.Where(col => col.gameObject.tag == "wall").ToArray().Length == 0)
-            {
-                trueAgent.transform.position = new Vector3(trueAgent.transform.position.x, 0, trueAgent.transform.position.z - 1);
-            }
+            targetPos = transform.position + new Vector3(0f, 0, -1f);
+        }
+
+        Collider[] blockTest = Physics.OverlapBox(targetPos, new Vector3(0.3f, 0.3f, 0.3f));
+        if (blockTest.Where(col => col.gameObject.tag == "wall").ToArray().Length == 0)
+        {
+            transform.position = targetPos;
+    }
-        Collider[] hitObjects = Physics.OverlapBox(trueAgent.transform.position, new Vector3(0.3f, 0.3f, 0.3f));
-        if (hitObjects.Where(col => col.gameObject.tag == "goal").ToArray().Length == 1)
+    void OnTriggerEnter(Collider col)
+    {
+        if (col.gameObject.CompareTag("goal"))
-        if (hitObjects.Where(col => col.gameObject.tag == "pit").ToArray().Length == 1)
+        if (col.gameObject.CompareTag("pit"))
-        }
-
-        //if (trainMode == "train") {
-        if (true)
-        {
-            academy.visualAgent.transform.position = trueAgent.transform.position;
-            academy.visualAgent.transform.rotation = trueAgent.transform.rotation;
        }
    }

--- a/unity-environment/Assets/ML-Agents/Examples/GridWorld/TFModels/GridWorld.bytes
+++ b/unity-environment/Assets/ML-Agents/Examples/GridWorld/TFModels/GridWorld.bytes
--- a/unity-environment/Assets/ML-Agents/Examples/GridWorld/TFModels/GridWorld.bytes.meta
+++ b/unity-environment/Assets/ML-Agents/Examples/GridWorld/TFModels/GridWorld.bytes.meta
 fileFormatVersion: 2
-guid: 9c75cb395cc9943838c0694ad4bc2604
-timeCreated: 1505542949
-licenseType: Free
+guid: 426162c47484e466d8378d2321a5617c
+timeCreated: 1515001510
+licenseType: Pro
+  externalObjects: {}
  userData: 
  assetBundleName: 
  assetBundleVariant: 
--- a/unity-environment/Assets/ML-Agents/Materials/MaterialsGrid/Floor.mat
+++ b/unity-environment/Assets/ML-Agents/Materials/MaterialsGrid/Floor.mat
        m_Offset: {x: 0, y: 0}
    - _EmissionMap:
        m_Texture: {fileID: 0}
-        m_Scale: {x: 0.9, y: 0.9}
+        m_Scale: {x: 3, y: 3}
-        m_Scale: {x: 0.9, y: 0.9}
+        m_Scale: {x: 3, y: 3}
        m_Offset: {x: 0.03, y: 0.06}
    - _MetallicGlossMap:
        m_Texture: {fileID: 0}
    - _Cutoff: 0.5
    - _DetailNormalMapScale: 1
    - _DstBlend: 0
-    - _GlossMapScale: 1
+    - _GlossMapScale: 0
    - _Glossiness: 0
    - _GlossyReflections: 1
    - _Metallic: 0
    - _UVSec: 0
    - _ZWrite: 1
    m_Colors:
-    - _Color: {r: 0.94509804, g: 0.9529412, b: 0.95686275, a: 1}
+    - _Color: {r: 0, g: 0, b: 0, a: 1}
    - _EmissionColor: {r: 0, g: 0, b: 0, a: 1}