Machine Teaching of Active Sequential Learners - 2019

Details

Title : Machine Teaching of Active Sequential Learners Author(s): Peltola, Tomi and Çelikok, Mustafa Mert and Daee, Pedram and Kaski, Samuel Link(s) : http://arxiv.org/abs/1809.02869

Rough Notes

Machine Teaching is the problem of finding the best training data that can guide a learning algorithm to a target model with minimal effort. Teachers that provide data consistent with the true distribution for sequential learners who actively choose queries can be sub-optimal for finite horizons. A Markov decision process is used, the dynamics being a model of the learner and the actions being the teacher's responses. The paper also looks at the problem of learning from a teacher that plans.

Learning is improved when we plan teaching and the learner has a model of the teacher. Can be of use to model strategic planning behaviour of users of interactive intelligent systems by assuming they are boundedly optimal teachers.

Emacs 29.4 (Org mode 9.6.15)