Koha9/Aimbot-ParallelEnv
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

bug fix

Browse Source 
fix target attack always win in first round.
This commit is contained in:
Koha9
2022-12-01 19:52:52 +09:00
parent 9585845ba2
commit 8570a5ba5e
13 changed files with 28088 additions and 27705 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Assets/Script/InGame/AgentWithGun.cs
+1 -1
View File
@@ -247,7 +247,7 @@ public class AgentWithGun : Agent
GameObject gotHitObj = hit.transform.gameObject;//获取受到Ray撞击的对象
gotHitObj.GetComponent<states>().ReactToHit(Damage, gameObject);
shoot = 0;
return targetCon.hitReward(gotHitObj.transform.position);
return targetCon.hitEnemyReward(gotHitObj.transform.position);
}
}
shoot = 0;
Assets/Script/InGame/ParameterContainer.cs
+27 -29
View File
@@ -25,12 +25,12 @@ public class ParameterContainer : MonoBehaviour
[Header("Dynamic Defaut Rewards")]
[Tooltip("Hit Enemy reward")]
public float hitRewardDefault = 60.0f;
//[Tooltip("Hit Enemy reward")]
//public float hitRewardDefault = 60.0f;
[Tooltip("Free mode Hit Enemy reward")]
public float hitTargetRewardDefault = 60.0f;
[Tooltip("Enemy down reward")]
public float killRewardDefault = 60.0f;
//[Tooltip("Enemy down reward")]
//public float killRewardDefault = 60.0f;
[Tooltip("Enemy down in area Reward")]
public float killTargetEnemyRewardDefault = 100.0f;
[Tooltip("stay in firebasesArea reward")]
@@ -53,13 +53,30 @@ public class ParameterContainer : MonoBehaviour
[Tooltip("free Win reward")]
public float freeWinRewardDefault = 100.0f;
[Header("Static Rewards")]
[Tooltip("Nothing happened reward")]
public float nonReward = -0.05f;
[Tooltip("Episode Lose reward")]
public float loseReward = -0.05f;
[Tooltip("Agent Do shoot action reward")]
public float shootReward = -0.1f;
[Tooltip("Hit Not target Enemy reward")]
public float hitReward = 30.0f;
[Tooltip("Not Target Enemy down reward")]
public float killReward = 40.0f;
[Tooltip("Agent Do shoot action but gun is not read")]
public float shootWithoutReadyReward = -0.15f;
[Tooltip("Kill bonus reward stack to nothing happend reward")]
public float killBonusReward = 0.0f;
[Header("Penalty Rewards")]
[Tooltip("Speed Penalty Reward")]
public float speedPanalty = 0f;
[Tooltip("view Panalty Reward")]
public float viewPanalty = 0f;
[Header("Dynamic Rewards")]
[Tooltip("Free mode Hit Enemy reward")]
public float hitTargetReward = 60.0f;
[Tooltip("Hit Enemy reward")]
public float hitReward = 30.0f;
[Tooltip("Enemy down reward")]
public float killReward = 40.0f;
[Tooltip("Enemy down in area Reward")]
public float killTargetEnemyReward = 80.0f;
[Tooltip("stay in firebasesArea reward")]
@@ -74,24 +91,6 @@ public class ParameterContainer : MonoBehaviour
[Tooltip("free Win reward")]
public float freeWinReward = 50.0f;
[Header("Static Rewards")]
[Tooltip("Nothing happened reward")]
public float nonReward = -0.05f;
[Tooltip("Episode Lose reward")]
public float loseReward = -0.05f;
[Tooltip("Agent Do shoot action reward")]
public float shootReward = -0.1f;
[Tooltip("Agent Do shoot action but gun is not read")]
public float shootWithoutReadyReward = -0.15f;
[Tooltip("Kill bonus reward stack to nothing happend reward")]
public float killBonusReward = 0.0f;
[Header("Penalty Rewards")]
[Tooltip("Speed Penalty Reward")]
public float speedPanalty = 0f;
[Tooltip("view Panalty Reward")]
public float viewPanalty = 0f;
private float targetTimeBonus = 0f;
private float areaTimeBonus = 0f;
private float freeTimeBonus = 0f;
@@ -131,12 +130,11 @@ public class ParameterContainer : MonoBehaviour
targetTimeBonus = targetTimeBonusPerSec * targetCon.leftTime;
}
hitReward = hitRewardDefault + freeTimeBonus;
hitTargetReward = hitTargetRewardDefault + freeTimeBonus;
killReward = killRewardDefault + freeTimeBonus;
hitTargetReward = hitTargetRewardDefault + targetTimeBonus;
killTargetEnemyReward = killTargetEnemyRewardDefault + targetTimeBonus;
inAreaReward = inAreaRewardDefault + areaTimeBonus;
// Win Rewards
goWinReward = goWinRewardDefault + targetTimeBonus;
attackWinReward = attackWinRewardDefault + targetTimeBonus;
defenceWinReward = defenceWinRewardDefault + targetTimeBonus;
Assets/Script/InGame/TargetController.cs
+27 -22
View File
@@ -51,6 +51,7 @@ public class TargetController : MonoBehaviour
private Vector3 targetPosition;
private Vector3 targetLocalPosition;
private bool firstRewardFlag = true;
private bool targetEnemySpawnFinish = false;
private SceneBlockContainer blockCont;
private EnemyContainer enemyCont;
private EnvironmentUIControl envUICon;
@@ -150,6 +151,7 @@ public class TargetController : MonoBehaviour
blockCont.thisBlock.initBlock(EnvironmentObj);
// set startDistance
firstRewardFlag = true;
targetEnemySpawnFinish = false;
}
else if (randTargetType > gotoProb + attackProb && randTargetType <= gotoProb + attackProb + defenceProb)
{
@@ -223,19 +225,6 @@ public class TargetController : MonoBehaviour
agentCharaCon.enabled = true;
}
// caulculate sceneReward if close to target then get great reward
public float getSceneReward(float nowDistance)
{
if (firstRewardFlag)
{
(lastDistance, _) = blockCont.getAgentTargetDistanceAndInside(AgentObj.transform.position);
firstRewardFlag = false;
}
float thisSceneReward = 0f;
thisSceneReward = paramCon.distanceReward * (lastDistance - nowDistance);
lastDistance = nowDistance;
return thisSceneReward;
}
// check over and get rewards
// 1 = success,2 = overtime,0 = notover
@@ -270,7 +259,7 @@ public class TargetController : MonoBehaviour
{
// keep on keeping on!
thisReward = (paramCon.inAreaReward * inArea) + getSceneReward(nowDistance);
thisReward = (paramCon.inAreaReward * inArea) + getDistanceReward(nowDistance);
endTypeInt = (int)EndType.Running;
}
break;
@@ -278,7 +267,7 @@ public class TargetController : MonoBehaviour
// attack
(nowDistance, inArea) = blockCont.getAgentTargetDistanceAndInside(AgentObj.transform.position);
envUICon.updateTargetGauge(blockCont.thisBlock.firebasesBelong, blockCont.thisBlock.belongMaxPoint);
if (blockCont.thisBlock.firebasesBelong >= blockCont.thisBlock.belongMaxPoint && blockCont.thisBlock.getInAreaNumber(group2Tag) <= 0)
if (blockCont.thisBlock.getInAreaNumber(group2Tag) <= 0 && targetEnemySpawnFinish)
{
// win
// let the area belongs to me and kill every enmy in this area.
@@ -286,7 +275,7 @@ public class TargetController : MonoBehaviour
//thisReward = (paramCon.inAreaReward * inArea) + getSceneReward(nowDistance);
endTypeInt = (int)EndType.Win;
}
else if (leftTime <= 0)
else if (leftTime <= 0 && targetEnemySpawnFinish)
{
// time out lose
thisReward = paramCon.loseReward;
@@ -296,7 +285,8 @@ public class TargetController : MonoBehaviour
else
{
// keep on keeping on!
thisReward = (paramCon.inAreaReward * inArea) + getSceneReward(nowDistance);
// thisReward = (paramCon.inAreaReward * inArea) + getDistanceReward(nowDistance);
targetEnemySpawnFinish = true;
endTypeInt = (int)EndType.Running;
}
break;
@@ -322,7 +312,7 @@ public class TargetController : MonoBehaviour
else
{
// keep on keeping on!
thisReward = (paramCon.inAreaReward * inArea) + getSceneReward(nowDistance);
// thisReward = (paramCon.inAreaReward * inArea) + getDistanceReward(nowDistance);
endTypeInt = (int)EndType.Running;
}
break;
@@ -354,6 +344,20 @@ public class TargetController : MonoBehaviour
return (endTypeInt, thisReward);
}
// caulculate sceneReward if close to target then get great reward
public float getDistanceReward(float nowDistance)
{
if (firstRewardFlag)
{
(lastDistance, _) = blockCont.getAgentTargetDistanceAndInside(AgentObj.transform.position);
firstRewardFlag = false;
}
float thisSceneReward = 0f;
thisSceneReward = paramCon.distanceReward * (lastDistance - nowDistance);
lastDistance = nowDistance;
return thisSceneReward;
}
// calculate kill reward base on killed enemy's position
public float killReward(Vector3 enemyPosition)
{
@@ -372,11 +376,12 @@ public class TargetController : MonoBehaviour
thisKillReward = paramCon.killReward;
}
}
else if(targetTypeInt == (int)Targets.Free)
else if (targetTypeInt == (int)Targets.Free)
{
// free mode kill
// free mode hit
thisKillReward = paramCon.killTargetEnemyReward;
}else
}
else
{
// goto & defence
thisKillReward = paramCon.killReward;
@@ -385,7 +390,7 @@ public class TargetController : MonoBehaviour
}
// calculate hit reward base on killed enemy's position and now mode
public float hitReward(Vector3 enemyPosition)
public float hitEnemyReward(Vector3 enemyPosition)
{
float thisHitReward = 0f;
if (targetTypeInt == (int)Targets.Attack)