Interactive learning strategies for acquiring categorical knowledge
While the ability to learn on its own is an important feature of a learning agent, another, equally important feature is ability to interact with its environment and to learn in an interaction with other cognitive agents and humans. A natural goal of an online learner is to speed up the learning process, therefore to achieve a good recognition performance as soon as possible. As we know from our everyday experience, a good teaching material facilitates learning, as well as a good teachers and a suitable interaction between the learner and the teacher do. Similar questions also arise in the case of online machine learning: which training samples to present to the learner, how the teaching process should be driven, what type of communication between the teacher and the learner facilitates learning?
Active learning approaches
In our research work we address the problem of interactive learning of categorical knowledge from the active learning perspective. We describe and implement several teacher and learner-driven approaches that require different levels of teacher competencies and consider different types of knowledge for selection of training samples. The experimental results show that the active learning approach outperforms the passive one and that the adaptation of the learning process to the learner’s knowledge significantly improves the learning performance.
We also analyze such interactive learning and define several learning strategies requiring different levels of tutor involvement and robot autonomy. We propose a new formal model for describing the learning strategies. The formalism takes into account different levels and types of communication between the robot and the tutor and different actions that can be undertaken. We also propose appropriate performance measures and show the experimental results of the evaluation of the proposed learning strategies.