Zobrazeno 1 - 10
of 64
pro vyhledávání: '"Givan, Robert"'
Autor:
Wu, Jia-Hong, Givan, Robert
Publikováno v:
Journal Of Artificial Intelligence Research, Volume 38, pages 687-755, 2010
Domain-specific features are important in representing problem structure throughout machine learning and decision-theoretic planning. In planning, once state features are provided, domain-independent algorithms such as approximate value iteration can
Externí odkaz:
http://arxiv.org/abs/1401.3847
We present a method for solving implicit (factored) Markov decision processes (MDPs) with very large state spaces. We introduce a property of state space partitions which we call epsilon-homogeneity. Intuitively, an epsilon-homogeneous partition grou
Externí odkaz:
http://arxiv.org/abs/1302.1533
We select policies for large Markov Decision Processes (MDPs) with compact first-order representations. We find policies that generalize well as the number of objects in the domain grows, potentially without bound. Existing dynamic-programming approa
Externí odkaz:
http://arxiv.org/abs/1301.0614
We propose a novel approach for density estimation with exponential families for the case when the true density may not fall within the chosen family. Our approach augments the sufficient statistics with features designed to accumulate probability ma
Externí odkaz:
http://arxiv.org/abs/1206.5036
Autor:
Givan, Robert Lawrence
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1996.
Includes bibliographical references (p. 97-101).
by Robert Lawrence Givan, Jr.
Ph.D.
Includes bibliographical references (p. 97-101).
by Robert Lawrence Givan, Jr.
Ph.D.
Externí odkaz:
http://hdl.handle.net/1721.1/11051
We have previously argued that the syntactic structure of natural language can be exploited to construct powerful polynomial time inference procedures. This paper supports the earlier arguments by demonstrating that a natural language based polynomia
Externí odkaz:
http://hdl.handle.net/1721.1/5971
Autor:
Givan, Robert, McAllester, David
We consider the concept of local sets of inference rules. Locality is a syntactic condition on rule sets which guarantees that the inference relation defined by those rules is polynomial time decidable. Unfortunately, determining whether a given rule
Externí odkaz:
http://hdl.handle.net/1721.1/5969
Autor:
Givan, Robert, McAllester, David
We consider the concept of a local set of inference rules. A local rule set can be automatically transformed into a rule set for which bottom-up evaluation terminates in polynomial time. The local-rule-set transformation gives polynomial-time evaluat
Externí odkaz:
http://arxiv.org/abs/cs/0007020
Publikováno v:
Mathematics of Operations Research, 2002 Nov 01. 27(4), 819-840.
Externí odkaz:
https://www.jstor.org/stable/3690469
Autor:
McAllester, David, Givan, Robert
We have argued elsewhere that first order inference can be made more efficient by using non-standard syntax for first order logic. In this paper we show how a fragment of English syntax under Montague semantics provides the foundation of a new infere
Externí odkaz:
http://hdl.handle.net/1721.1/6524