2019/07/24 by Chang, Yen-Wei, Peng, Wen-Hsiao
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)
paper · doi:10.48550/arxiv.1907.10500
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.