Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization

Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization Yangyang Zhao author Mehdi Dastani author Jinchuan Long author Zhenyu Wang author Shihan Wang author 2024 text journal article Transactions of the Association for Computational Linguistics continuing MIT Press Cambridge, MA periodical academic journal zhao-etal-2024-rescue 10.1162/tacl_a_00717 https://aclanthology.org/2024.tacl-1.86/ 2024 12 1578 1596