Sciweavers

312 search results - page 30 / 63
» Learning Partially Observable Deterministic Action Models
Sort
View
AIPS
2008
13 years 10 months ago
HiPPo: Hierarchical POMDPs for Planning Information Processing and Sensing Actions on a Robot
Flexible general purpose robots need to tailor their visual processing to their task, on the fly. We propose a new approach to this within a planning framework, where the goal is ...
Mohan Sridharan, Jeremy L. Wyatt, Richard Dearden
AAAI
2010
13 years 9 months ago
Automatic Derivation of Finite-State Machines for Behavior Control
Finite-state controllers represent an effective action selection mechanisms widely used in domains such as video-games and mobile robotics. In contrast to the policies obtained fr...
Blai Bonet, Héctor Palacios, Hector Geffner
ICML
2004
IEEE
14 years 8 months ago
Learning and discovery of predictive state representations in dynamical systems with reset
Predictive state representations (PSRs) are a recently proposed way of modeling controlled dynamical systems. PSR-based models use predictions of observable outcomes of tests that...
Michael R. James, Satinder P. Singh
AAAI
2004
13 years 9 months ago
An Instance-Based State Representation for Network Repair
We describe a formal framework for diagnosis and repair problems that shares elements of the well known partially observable MDP and cost-sensitive classification models. Our cost...
Michael L. Littman, Nishkam Ravi, Eitan Fenson, Ri...
ALT
2005
Springer
14 years 4 months ago
Defensive Universal Learning with Experts
This paper shows how universal learning can be achieved with expert advice. To this aim, we specify an experts algorithm with the following characteristics: (a) it uses only feedba...
Jan Poland, Marcus Hutter