14 search results - page 2 / 3 » Learning Options for an MDP from Demonstrations |
ICRA
2010
IEEE
13 years 3 months ago
2010
IEEE
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...
KCAP
2009
ACM
13 years 11 months ago
2009
ACM
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...
Publication
We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous w...
BIBE
2005
IEEE
13 years 10 months ago
2005
IEEE
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...
IUI
1997
ACM
13 years 9 months ago
1997
ACM
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...