V2.8 移动算法更新

过去X与Y可同时达到maxspeed致使速度会超过maxspeed，本次修正了该错误。
追加移动Penalty。

Assets/Script/InGame/AgentWithGun.cs

@@ -33,9 +33,10 @@ public class AgentWithGun : Agent
     public Camera thisCam;
 
     [Header("GetAxis() Simulate")]
-    public float MoveSpeed = 2.0f;
+    public float MoveSpeed = 9.0f;
     public float vX = 0f;
     public float vZ = 0f;
+    public Vector3 thisMovement;
     public float acceleration = 0.1f; // 加速度
     public float mouseXSensitivity = 100;
     public float mouseYSensitivity = 200;
@@ -107,7 +108,7 @@ public class AgentWithGun : Agent
     // moveAgent 用于模拟Input.GetAxis移动
     public void moveAgent(int vertical, int horizontal)
     {
-        Vector3 thisMovement;
+        // Vector3 thisMovement;
 
         if (horizontal != 0)//当按下按键（水平方向）
         {
@@ -170,9 +171,13 @@ public class AgentWithGun : Agent
                 vZ = 0;
             }
         }
-        thisMovement = (transform.forward * vZ + transform.right * vX) * MoveSpeed;
+        thisMovement = (transform.forward * vZ + transform.right * vX);
         //PlayerController下的.Move为实现物体运动的函数
         //Move()括号内放入一个Vector3类型的量，本例中为Player_Move
+        if (thisMovement.magnitude > MoveSpeed)
+        {
+            thisMovement = thisMovement.normalized * MoveSpeed;
+        }
         PlayerController.Move(thisMovement * Time.deltaTime);
         // update Key Viewer
     }
@@ -362,7 +367,7 @@ public class AgentWithGun : Agent
 
     // ------------Reward--------------
     // rewardCalculate 计算本动作的Reward
-    public float rewardCalculate(float sceneReward,float mouseX)
+    public float rewardCalculate(float sceneReward,float mouseX,float movement)
     {
         float epreward = 0f;
         // 击杀reward判断
@@ -383,6 +388,7 @@ public class AgentWithGun : Agent
         epreward += ballistic() + sceneReward;
         // facing reward
         epreward += facingReward();
+        // Penalty
         // spin penalty
         spinRecord.Add(mouseX);
         if (spinRecord.Count >= paramContainer.spinRecordMax)
@@ -398,6 +404,11 @@ public class AgentWithGun : Agent
         {
             epreward -= Math.Abs(mouseX) * paramContainer.mousePenalty;
         }
+        // move penalty
+        if (movement != 0)
+        {
+            epreward -= paramContainer.movePenalty;
+        }
         return epreward;
     }
 
@@ -484,7 +495,7 @@ public class AgentWithGun : Agent
         float sceneReward = 0f;
         float endReward = 0f;
         (finishedState, sceneReward, endReward) = targetCon.checkOverAndRewards();
-        float thisRoundReward = rewardCalculate(sceneReward+ endReward,Mouse_X);
+        float thisRoundReward = rewardCalculate(sceneReward+ endReward,Mouse_X,Math.Abs(vertical)+Math.Abs(horizontal));
         if (hudController.chartOn)
         {
             EnvUICon.updateChart(thisRoundReward);

Assets/Script/InGame/ParameterContainer.cs

@@ -76,8 +76,8 @@ public class ParameterContainer : MonoBehaviour
     public float shootTargetAreaReward = 5.0f;
 
     [Header("Penalty Rewards")]
-    [Tooltip("Speed Penalty Reward")]
-    public float speedPenalty = 0f;
+    [Tooltip("move Penalty Reward")]
+    public float movePenalty = 0f;
     [Tooltip("spiiiiiiin Panalty Reward")]
     public float spinPenalty = 0f;
     [Tooltip("while move mouse a little bit's penalty")]

Assets/Script/InGame/TargetController.cs

@@ -264,8 +264,8 @@ public class TargetController : MonoBehaviour
                 (nowDistance, inArea) = blockCont.getAgentTargetDistanceAndInside(AgentObj.transform.position);
                 envUICon.updateTargetGauge(blockCont.thisBlock.firebasesBelong, blockCont.thisBlock.belongMaxPoint);
                 float areaTargetReward = getDistanceReward(nowDistance, inArea);
-                // if (blockCont.thisBlock.firebasesBelong >= blockCont.thisBlock.belongMaxPoint)
-                if(inArea != 0)
+                //if(inArea != 0)
+                if (blockCont.thisBlock.firebasesBelong >= blockCont.thisBlock.belongMaxPoint)
                 {
                     // win
                     // let the area belongs to me
@@ -284,7 +284,6 @@ public class TargetController : MonoBehaviour
                 else
                 {
                     // keep on keeping on!
-
                     thisReward = areaTargetReward;
                     endReward = 0;
                     endTypeInt = (int)EndType.Running;
@@ -392,6 +391,7 @@ public class TargetController : MonoBehaviour
         float thisSceneReward = 0f;
         if (inarea != 0)
         {
+            // in area
             thisSceneReward = paramCon.inAreaReward;
         }
         else