主題

狗頭人哨兵追逐 4

夏洛爾 | 2022-12-05 10:42:42 | 巴幣 2 | 人氣 175

Kobold Sentinel Run V4

實驗目標:

1.進入靜立狀態後，進入追逐狀態，在追逐狀態下，要能持續跑至接近目標的距離內

2.動作引導為雙臂展開身體前傾的帥氣奔跑動作

實驗設計:

1.任何弱點觸地皆失敗 (尾巴、武器和Calf並非弱點)

2.使用ClampReward

if(koboldBodies[i].damageCoef > 0f){clampReward += -0.1f * koboldBodies[i].damageCoef;}

3.

//Set: judge.endEpisode = false//Set: nearModeRange = 1f//Set: weapon, tail is not weakness. If is, Stand would back to GetUp//Set: calf is not weaknessif(weaknessOnGround){// LogWeaknessOnGround();if(inferenceMode){brainMode = BrainMode.GetUp;SetModel("KoboldGetUp", getUpBrain);behaviorParameters.BehaviorType = BehaviorType.InferenceOnly;}else{AddReward(-1f);judge.outLife++;judge.Reset();return;}}else if(koboldRoot.localPosition.y < -10f){if(inferenceMode){brainMode = BrainMode.GetUp;SetModel("KoboldGetUp", getUpBrain);behaviorParameters.BehaviorType = BehaviorType.InferenceOnly;}else{AddReward(-1f);judge.outY++;judge.Reset();return;}}else{targetSmoothPosition = targetPositionBuffer.GetSmoothVal();headDir = targetSmoothPosition - stageBase.InverseTransformPoint(koboldHeadRb.position);rootDir = targetSmoothPosition - stageBase.InverseTransformPoint(koboldRootRb.position);flatTargetVelocity = rootDir;flatTargetVelocity.y = 0f;targetDistance = flatTargetVelocity.magnitude;//Naruto ArmVector3 flatLeftDir = Vector3.Cross(flatTargetVelocity, Vector3.up);lookAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldHead.up, headDir));//Side LookupAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldHead.forward, flatLeftDir));aimVelocity = flatTargetVelocity.normalized;aimVelocity.y = 0.2f;//LeanVector3 leanDir = rootAimRot * flatTargetVelocity;spineUpAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldSpine.right * -1f, leanDir));rootUpAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldRoot.up, leanDir));leftUpperArmAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldLeftUpperArm.right, leftUpperArmAimRot * flatTargetVelocity));leftForeArmAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldLeftForeArm.right, leftForeArmAimRot * flatTargetVelocity));rightUpperArmAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldRightUpperArm.right, rightUpperArmAimRot * flatTargetVelocity));rightForeArmAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldRightForeArm.right, rightForeArmAimRot * flatTargetVelocity));weaponAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldWeapon.up, weaponAimRot * flatTargetVelocity));tailRootAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldTailRoot.right, flatTargetVelocity));tailMidAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldTailMid.right, flatTargetVelocity));tailTopAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldTailTop.right, flatTargetVelocity));leftThighAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldLeftThigh.forward * -1f, flatLeftDir));rightThighAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(koboldRightThigh.forward * -1f, flatLeftDir));avgVelocity = velocityBuffer.GetSmoothVal();velocityAngle = Vector3.Angle(avgVelocity, aimVelocity);velocityAngleCoef = Mathf.InverseLerp(180f, 0f, velocityAngle);flatVelocity = avgVelocity;flatVelocity.y = 0f;flatVelocityManitude = flatVelocity.magnitude;velocityCoef = Mathf.InverseLerp(0f, 10f, Vector3.Project(avgVelocity, aimVelocity).magnitude );flatVelocityAngle = Vector3.Angle(flatVelocity, flatTargetVelocity);if(!inferenceMode){if(targetDistance > nearModeRange){if(Time.fixedTime - landingMoment > landingBufferTime){bool outSpeed = flatVelocityManitude < Mathf.Lerp(0f, 7f, (Time.fixedTime - landingMoment - landingBufferTime)/4f);bool outDirection = flatVelocityAngle > Mathf.Lerp(180f, 10f, (Time.fixedTime - landingMoment - landingBufferTime)/4f);float motionLimit = Mathf.Lerp(0f, 0.5f, (Time.fixedTime - landingMoment - landingBufferTime)/4f);float motionLimit2 = Mathf.Lerp(0f, 0.7f, (Time.fixedTime - landingMoment - landingBufferTime)/4f);bool outMotion = lookAngle < motionLimit2 || upAngle < motionLimit2 || leftThighAngle < motionLimit2 || rightThighAngle < motionLimit2 || spineUpAngle < motionLimit || rootUpAngle < motionLimit || leftUpperArmAngle < motionLimit || leftForeArmAngle < motionLimit || rightUpperArmAngle < motionLimit || rightForeArmAngle < motionLimit|| weaponAngle < motionLimit;if( outSpeed || outDirection || outMotion){AddReward(-1f);if(outSpeed){judge.outSpeed++;}if(outDirection){judge.outDirection++;}if(outMotion){judge.outMotion++;}judge.Reset();return;}}lastReward = (velocityAngleCoef + velocityCoef) * 0.02f + (lookAngle+upAngle) * 0.0125f + (leftThighAngle+rightThighAngle) * 0.0075f+ (spineUpAngle+rootUpAngle) * 0.005f+ (leftUpperArmAngle+leftForeArmAngle+rightUpperArmAngle+rightForeArmAngle+weaponAngle+tailRootAngle+tailMidAngle+tailTopAngle ) * 0.001f+ (1f - exertionRatio) * 0.002f;if(useClampReward){lastReward = lastReward+clampReward;if(lastReward < 0f) lastReward = 0f;}totalReward += lastReward;AddReward( lastReward );}// else if(targetDistance > 1.5f)else{// AddReward(1f);judge.survived++;judge.Reset();return;}}}

//大致來說，

--1.獎勵視線，並使用Force Sharping

--2.獎勵投影至"跑動推薦向量"的速度和角度，並使用Force Sharping

--3.獎勵Root、Spine、雙臂特定向量(forward/up/right)符合指定角度，並使用Force Sharping

--4.獎勵尾巴全體符合指定角度，但"並不使用Force Sharping"

--5.獎勵減少動作變化

實驗時間:

Step: 5e7

Time Elapsed: 73029s (20.29hr)

實驗結果:

實驗結果為大致成功，小部分失敗

以觀測結論來說，比例1.3以上的狗頭人哨兵都變得可以進行全程奔跑