Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts
This work improves goal-oriented visual dialog systems, which is important for human-computer interaction applications, but it is incremental as it builds on existing methods.
The paper addresses learning a questioner for goal-oriented visual dialog by combining imitation learning from analytic experts with reinforcement learning, achieving state-of-the-art performance on the GuessWhat?! dataset.
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.