qlearning.py 文件源码

def evaluate(self, environment, model=QModel.ACTION_VALUE_NETWORK):
        if check_rank(environment.shape, get_rank(self._input_shape)):
            environment = environment.reshape((1,) + environment.shape)

        # Move data if necessary
        if self._gpu_device is not None:
            environment = cuda.to_gpu(environment, self._gpu_device)

        if model == QModel.ACTION_VALUE_NETWORK:
            output = self._model(environment)
        else:
            output = self._target(environment)

        return cuda.to_cpu(output.data)