@inproceedings{kachuee-lee-2023-constrained,
    title = "Constrained Policy Optimization for Controlled Self-Learning in Conversational {AI} Systems",
    author = "Kachuee, Mohammad  and
      Lee, Sungjin",
    editor = "Sitaram, Sunayana  and
      Beigman Klebanov, Beata  and
      Williams, Jason D",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2023.acl-industry.5/",
    doi = "10.18653/v1/2023.acl-industry.5",
    pages = "43--52",
    abstract = "Recently, self-learning methods based on user satisfaction metrics and contextual bandits have shown promising results to enable consistent improvements in conversational AI systems. However, directly targeting such metrics by off-policy bandit learning objectives often increases the risk of making abrupt policy changes that break the current user experience. In this study, we introduce a scalable framework for supporting fine-grained exploration targets for individual domains via user-defined constraints. For example, we may want to ensure fewer policy deviations in business-critical domains such as shopping, while allocating more exploration budget to domains such as music. We present a novel meta-gradient learning approach that is scalable and practical to address this problem. The proposed method adjusts constraint violation penalty terms adaptively through a meta objective that encourages balanced constraint satisfaction across domains. We conducted extensive experiments on a real-world conversational AI and using a set of realistic constraint benchmarks. The proposed approach has been deployed in production for a large-scale commercial assistant, enabling the best balance between the policy value and constraint satisfaction rate."
}