Doyle Chase V5

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.動作引導為類似火影跑的開臂奔跑動作

1.任何弱點觸地皆失敗 (尾巴和劍並非弱點)

2.targetSmoothPosition = targetPositionBuffer.GetSmoothVal();headDir = targetSmoothPosition - stageBase.InverseTransformPoint(doyleHeadRb.position);rootDir = targetSmoothPosition - stageBase.InverseTransformPoint(doyleRootRb.position);flatTargetVelocity = rootDir;flatTargetVelocity.y = 0f;targetDistance = flatTargetVelocity.magnitude;lookAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(doyleHead.up, headDir));upAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(doyleHead.right * -1f, Vector3.up));aimVelocity = flatTargetVelocity.normalized;aimVelocity.y = 0.2f;//LeanVector3 leanDir = aimVelocity;leanDir.y = 0.1f;spineUpAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(doyleSpine.right * -1f, leanDir));rootUpAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(doyleRoot.up, leanDir));//Naruto ArmVector3 flatLeftDir = Vector3.Cross(flatTargetVelocity, Vector3.up);leftUpperArmAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(doyleLeftUpperArm.right, leftUpperArmAimRot * flatTargetVelocity));leftForeArmAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(doyleLeftForeArm.right, leftForeArmAimRot * flatTargetVelocity));rightUpperArmAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(doyleRightUpperArm.right, rightUpperArmAimRot * flatTargetVelocity));rightForeArmAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(doyleRightForeArm.right, rightForeArmAimRot * flatTargetVelocity));swordAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(doyleSword.up, swordAimRot * flatTargetVelocity));leftThighAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(doyleLeftThigh.forward * -1f, flatLeftDir));rightThighAngle = Mathf.InverseLerp(180f, 0f, Vector3.Angle(doyleRightThigh.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, 15f, Vector3.Project(avgVelocity, aimVelocity).magnitude );flatVelocityAngle = Vector3.Angle(flatVelocity, flatTargetVelocity);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, 0.7f, (Time.fixedTime - landingMoment - landingBufferTime)/5f);float motionLimit2 = Mathf.Lerp(0f, 0.9f, (Time.fixedTime - landingMoment - landingBufferTime)/5f);bool outMotion = lookAngle < motionLimit2 || upAngle < motionLimit2 || leftThighAngle < motionLimit2 || rightThighAngle < motionLimit2 || spineUpAngle < motionLimit || rootUpAngle < motionLimit || leftUpperArmAngle < motionLimit || leftForeArmAngle < motionLimit || rightUpperArmAngle < motionLimit || rightForeArmAngle < motionLimit || swordAngle < 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) * 0.004f + (lookAngle+upAngle) * 0.002f + (leftThighAngle+rightThighAngle) * 0.001f+ (spineUpAngle+rootUpAngle) * 0.001f + (leftUpperArmAngle+leftForeArmAngle+rightUpperArmAngle+rightForeArmAngle+swordAngle) * 0.001f+ (1f - exertionRatio) * 0.0005f;totalReward += lastReward;AddReward( lastReward );}

//大致來說，

--1.獎勵視線

--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和Spine前傾，獎勵雙臂方向平行指定向量，並使用Force Sharping

--4.獎勵減少動作變化

3.取消 End episode on maximum of 20s