Sciweavers

2972 search results - page 328 / 595
» Representing the Knowledge of a Robot
Sort
View
ECAI
2008
Springer
15 years 8 months ago
Belief revision with reinforcement learning for interactive object recognition
From a conceptual point of view, belief revision and learning are quite similar. Both methods change the belief state of an intelligent agent by processing incoming information. Ho...
Thomas Leopold, Gabriele Kern-Isberner, Gabriele P...
FLOPS
2008
Springer
15 years 8 months ago
Integrating Answer Set Reasoning with Constraint Solving Techniques
Abstract. The paper introduces a collection of knowledge representation languages, V(C), parametrised over a class C of constraints. V(C) is an extension of both CR-Prolog and CASP...
Veena S. Mellarkod, Michael Gelfond
I3
2007
15 years 8 months ago
Referent Tracking and its Applications
Referent tracking (RT) is a new paradigm, based on unique identification, for representing and keeping track of particulars. It was first introduced to support the entry and retri...
Werner Ceusters, Barry Smith
IJCAI
2007
15 years 8 months ago
Recursive Random Fields
A formula in first-order logic can be viewed as a tree, with a logical connective at each node, and a knowledge base can be viewed as a tree whose root is a conjunction. Markov l...
Daniel Lowd, Pedro Domingos
IJCAI
2007
15 years 8 months ago
Using Linear Programming for Bayesian Exploration in Markov Decision Processes
A key problem in reinforcement learning is finding a good balance between the need to explore the environment and the need to gain rewards by exploiting existing knowledge. Much ...
Pablo Samuel Castro, Doina Precup