Skip to main content Skip to main navigation


Structured Apprenticeship Learning

Abdeslam Boularias; Oliver Krömer; Jan Peters
In: Peter A. Flach; Tijl De Bie; Nello Cristianini (Hrsg.). Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2012, Proceedings, Part II. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD-2012), September 24-28, Bristol, United Kingdom, Pages 227-242, Lecture Notes in Artificial Intelligence (LNAI), Vol. 7524, Springer, 2012.


We propose a graph-based algorithm for apprenticeship learning when the reward features are noisy. Previous apprenticeship learning techniques learn a reward function by using only local state features. This can be a limitation in practice, as often some features are misspecified or subject to measurement noise. Our graphical framework, inspired from the work on Markov Random Fields, allows to alleviate this problem by propagating information between states, and rewarding policies that choose similar actions in adjacent states. We demonstrate the advantage of the proposed approach on grid-world navigation problems, and on the problem of teaching a robot to grasp novel objects in simulation.

Weitere Links