Learning how to learn: an adaptive dialogue agent for incrementally learning visually grounded word meanings
This addresses the challenge of efficient interactive learning for AI systems, though it is incremental as it builds on existing methods and datasets.
The paper tackles the problem of an adaptive dialogue agent learning visually grounded word meanings from a human tutor, achieving a better trade-off between classifier accuracy and tutoring costs compared to hand-crafted rule-based policies.
We present an optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data. Within a life-long interactive learning period, the agent, trained using Reinforcement Learning (RL), must be able to handle natural conversations with human users and achieve good learning performance (accuracy) while minimising human effort in the learning process. We train and evaluate this system in interaction with a simulated human tutor, which is built on the BURCHAK corpus -- a Human-Human Dialogue dataset for the visual learning task. The results show that: 1) The learned policy can coherently interact with the simulated user to achieve the goal of the task (i.e. learning visual attributes of objects, e.g. colour and shape); and 2) it finds a better trade-off between classifier accuracy and tutoring costs than hand-crafted rule-based policies, including ones with dynamic policies.