Qfunction_approx.py 文件源码

def __init__(self, T, L, backup):
        self.backup = backup
        self.T = T
        self.L = L
        self.pre_process = PolynomialFeatures(degree=2, include_bias=False)
        if self.backup['name'] == 'sampling':
            self.Q = linear_model.SGDRegressor(loss='huber', penalty='l2', learning_rate='invscaling', eta0=0.1, power_t=0.25, warm_start=False)
        elif self.backup['name'] == 'doubleQ':
            self.Q_1 = linear_model.SGDRegressor(loss='huber', penalty='l2', learning_rate='invscaling', eta0=0.1, power_t=0.25, warm_start=False)
            self.Q_2 = linear_model.SGDRegressor(loss='huber', penalty='l2', learning_rate='invscaling', eta0=0.1, power_t=0.25, warm_start=False)
        elif self.backup['name'] == 'replay buffer':
            self.Q = linear_model.SGDRegressor(loss='huber', penalty='l2', learning_rate='invscaling', eta0=0.1, power_t=0.25, warm_start=False)
            self.buff = []
        else:
            print "Illegal Backup Type"