44 lines
1.5 KiB
Python
44 lines
1.5 KiB
Python
|
import numpy as np
|
||
|
|
|
||
|
|
class rewardAI(object):
|
||
|
|
def __init__(self,nonReward, shootReward, shootWithoutReadyReward, hitReward, winReward, loseReward, killReward):
|
||
|
|
self.nonReward = nonReward
|
||
|
|
self.shootReward = shootReward
|
||
|
|
self.shootWithoutReadyReward = shootWithoutReadyReward
|
||
|
|
self.hitReward = hitReward
|
||
|
|
self.winReward = winReward
|
||
|
|
self.loseReward = loseReward
|
||
|
|
self.killReward = killReward
|
||
|
|
|
||
|
|
def getRewards(self,remainTime):
|
||
|
|
nonR = self.getnonReward()
|
||
|
|
shootR = self.getshootReward()
|
||
|
|
shootWithoutReadyR = self.getshootWithoutReadyReward()
|
||
|
|
hitR = self.gethitReward()
|
||
|
|
winR = self.getwinReward(remainTime)
|
||
|
|
loseR = self.getloseReward()
|
||
|
|
killR = self.getkillReward(remainTime)
|
||
|
|
|
||
|
|
rewards = np.array([[nonR,
|
||
|
|
shootR,
|
||
|
|
shootWithoutReadyR,
|
||
|
|
hitR,
|
||
|
|
winR,
|
||
|
|
loseR,
|
||
|
|
killR]], dtype=np.float)
|
||
|
|
return rewards
|
||
|
|
|
||
|
|
def getnonReward (self):
|
||
|
|
return self.nonReward
|
||
|
|
def getshootReward(self):
|
||
|
|
return self.shootReward
|
||
|
|
def getshootWithoutReadyReward(self):
|
||
|
|
return self.shootWithoutReadyReward
|
||
|
|
def gethitReward(self):
|
||
|
|
return self.hitReward
|
||
|
|
def getwinReward(self,time):
|
||
|
|
return (self.winReward + time)
|
||
|
|
def getloseReward(self):
|
||
|
|
return self.loseReward
|
||
|
|
def getkillReward(self,time):
|
||
|
|
return (self.killReward + time)
|