標題: LEARNING GOAL-ORIENTED VISUAL DIALOG AGENTS: IMITATING AND SURPASSING ANALYTIC EXPERTS
作者: Chang, Yen-Wei
Peng, Wen-Hsiao
交大名義發表
National Chiao Tung University
公開日期: 1-Jan-2019
摘要: This paper tackles the problem of learning a questioner in the goal-oriented visual dialog task. Several previous works adopt model-free reinforcement learning. Most pretrain the model from a finite set of human-generated data. We argue that using limited demonstrations to kick-start the questioner is insufficient due to the large policy search space. Inspired by a recently proposed information theoretic approach, we develop two analytic experts to serve as a source of high-quality demonstrations for imitation learning. We then take advantage of reinforcement learning to refine the model towards the goal-oriented objective. Experimental results on the GuessWhat?! dataset show that our method has the combined merits of imitation and reinforcement learning, achieving the state-of-the-art performance.
URI: http://dx.doi.org/10.1109/ICME.2019.00096
http://hdl.handle.net/11536/153328
ISBN: 978-1-5386-9552-4
ISSN: 1945-7871
DOI: 10.1109/ICME.2019.00096
期刊: 2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)
起始頁: 520
結束頁: 525
Appears in Collections:Conferences Paper