Abstract— We consider the problem of apprenticeship learning when the expert’s demonstration covers only a small part of a large state space. Inverse Reinforcement Learning (IR...
As computational learning agents move into domains that incur real costs (e.g., autonomous driving or financial investment), it will be necessary to learn good policies without n...
We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous w...
One of the major problems in biological data integration is that many data sources are stored as flat-files, with a variety of different layouts. Integrating data from such sour...
Kaushik Sinha, Xuan Zhang, Ruoming Jin, Gagan Agra...
This paper describes ActionStreams, a system for inducing task models from observations of user activity. The model can represent several task structures: hierarchy, variable sequ...