test_action_value.py 文件源码

def setUp(self):

        def evaluator(actions):
            # negative square norm of actions
            return -F.sum(actions ** 2, axis=1)

        self.evaluator = evaluator

        if self.has_maximizer:
            def maximizer():
                return chainer.Variable(np.zeros(
                    (self.batch_size, self.action_size), dtype=np.float32))
        else:
            maximizer = None
        self.maximizer = maximizer
        self.av = action_value.SingleActionValue(
            evaluator=evaluator, maximizer=maximizer)