Experience as source for anticipation and planning : Experiential policy learning for target-driven recommendation dialogues

• Main Authors: DAO, Quang Huy, DENG, Yang, BUI, Khanh-Huyen, LE, Dung D., LIAO, Lizi
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Recommendation dialogues; Experiential policy learning; EPL; Large Language Models; LLMs; Artificial Intelligence and Robotics; Computer Sciences
• Online Access: https://ink.library.smu.edu.sg/sis_research/9617; https://ink.library.smu.edu.sg/context/sis_research/article/10617/viewcontent/2743_Experience_as_Source_for_.pdf
• Institution: Singapore Management University

Target-driven recommendation dialogues present unique challenges in dialogue management due to the necessity of anticipating user interactions for successful conversations. Current methods face significant limitations: (I) inadequate capabilities for conversation anticipation, (II) computational ine...