def getPrototypeDistribution(i): dist = [] prototype = prototypes[i] for state in range(maxState): tempPrototype = Prototype(numActions, stateDimension) tempPrototype.setFixed([state/float(maxState)], 0) tempFeatureDiff = tempPrototype.calculateDiff(prototype) membershipGrade = float(exp(-(tempFeatureDiff*tempFeatureDiff)/2*prototype.getFeatureWidth())) dist.append(membershipGrade*prototype.getTheta()) return dist
def getQ(state, action):
tempPrototype = Prototype(numActions, stateDimension)
tempPrototype.setFixed([state/float(maxState)], action)
thetaSum = 0
for prototype in prototypes:
tempFeatureDiff = tempPrototype.calculateDiff(prototype)
membershipGrade = float(exp(-(tempFeatureDiff*tempFeatureDiff)/2*prototype.getFeatureWidth()))
# print('state: ' + str(tempPrototype.state) + ' prototype.state: ' + str(prototype.state) + ' membershipGrade: ' + str(membershipGrade) + ' theta: ' + str(prototype.getTheta()))
# raw_input("Press Enter to continue...")
thetaSum += prototype.getTheta() * membershipGrade
# print('thetaSum: ' + str(thetaSum))
# raw_input("Press Enter to continue...")
return thetaSum
def getPrototypeIndex(self, state, prototypeIndex): tempPrototype = Prototype(1, self.stateDimension) tempPrototype.setFixed([state/float(self.maxState + 1)], 0) pGrade = [0]*self.numGroups for i in range(len(self.prototypes)): prototype = self.prototypes[i] tempFeatureDiff = tempPrototype.calculateDiff(prototype) membershipGrade = float(exp(-(tempFeatureDiff*tempFeatureDiff)/2*prototype.getFeatureWidth()))#/sqrt(2*prototype.getFeatureWidth()*pi) if pGrade[prototype.group] < membershipGrade: prototypeIndex[prototype.group] = i pGrade[prototype.group] = membershipGrade return [p/sum(pGrade) for p in pGrade]
def getPrototypeIndex(self, state, prototypeIndex):
tempPrototype = Prototype(1, self.stateDimension)
tempPrototype.setFixed([state / float(self.maxState + 1)], 0)
pGrade = [0] * self.numGroups
for i in range(len(self.prototypes)):
prototype = self.prototypes[i]
tempFeatureDiff = tempPrototype.calculateDiff(prototype)
membershipGrade = float(
exp(-(tempFeatureDiff * tempFeatureDiff) / 2 *
prototype.getFeatureWidth())
) #/sqrt(2*prototype.getFeatureWidth()*pi)
if pGrade[prototype.group] < membershipGrade:
prototypeIndex[prototype.group] = i
pGrade[prototype.group] = membershipGrade
return [p / sum(pGrade) for p in pGrade]
def learn(state1, action1, reward, state2):
# maxQ = -float('inf')
# for a in range(numActions):
# tempQ = getQ(state2, a)
# if (maxQ < tempQ):
# maxQ = tempQ
### sarsa
maxQ = getQ(state2, 0)
preQ = getQ(state1, action1)
delta = reward + gamma*maxQ - preQ
tempPrototype = Prototype(numActions, stateDimension)
tempPrototype.setFixed([state1/float(maxState)], action1)
for prototype in prototypes:
tempFeatureDiff = tempPrototype.calculateDiff(prototype)
membershipGrade = float(exp(-(tempFeatureDiff*tempFeatureDiff)/2*prototype.getFeatureWidth()))
prototype.setTheta(prototype.getTheta() + alpha * delta * membershipGrade/numPrototypes)
