@article{zhao-etal-2024-rescue, title = "Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization", author = "Zhao, Yangyang and Dastani, Mehdi and Long, Jinchuan and Wang, Zhenyu and Wang, Shihan", journal = "Transactions of the Association for Computational Linguistics", volume = "12", year = "2024", address = "Cambridge, MA", publisher = "MIT Press", url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.tacl-1.86/", doi = "10.1162/tacl_a_00717", pages = "1578--1596" }