Adapting a Spoken Dialogue System to the user's satisfaction is supposed to result in more successful dialogues. In this thesis, Gaussian processes are used to model a policy for a statistical Spoken Dialogue System and the Interaction Quality (IQ) metric which is a measure for the user's satisfaction is used to train this policy. As the policy decides which actions are taken next at a particular point, the dialogue  ow is thus adapted to the IQ. Afterwards, it is investigated whether the incorporation of the IQ metric is benecial. Therefore, dierent learning strategies with and without the IQ metric are used to train dierent policies. Then, the performance of all trained policies is evaluated regarding dialogue completion, task success, the average length of a dialogue and the average IQ value at the end of a dialogue.