learningAgent.py 文件源码

def __init__(self,player_number,epsilon=0.5,discount=0.8,alpha=1e-4,mode='test',pickle_name = None,lr_decay_fn = None):
        Agent.__init__(self,player_number)
        self.epsilon = epsilon
        self.discount = discount
        self.alpha = alpha
        self.setLearningTarget()
        self.lr_decay = lr_decay_fn
        if mode == 'train':
            self.train = True
        elif mode == 'test':
            self.train = False
        else:
            print ('no mode \'',mode,'\' for QlearningAgent')
            raise Exception

        self.reset()
        if pickle_name != None:
            self.load(pickle_name)
        print ('epsilon :',self.epsilon)   
        print ('learning :',self.alpha)
        print ('discount :',self.discount)