Sciweavers

1095 search results - page 110 / 219
» Preprocessing of Intractable Problems
Sort
View
ATAL
2008
Springer
15 years 3 months ago
Reinforcement learning for DEC-MDPs with changing action sets and partially ordered dependencies
Decentralized Markov decision processes are frequently used to model cooperative multi-agent systems. In this paper, we identify a subclass of general DEC-MDPs that features regul...
Thomas Gabel, Martin A. Riedmiller
DAGSTUHL
2007
15 years 2 months ago
QUAD: Overview and Recent Developments
We give an outline of the specification and provable security features of the QUAD stream cipher proposed at Eurocrypt 2006 [6]. The cipher relies on the iteration of a multivaria...
David Arditti, Côme Berbain, Olivier Billet,...
UAI
2001
15 years 2 months ago
Hypothesis Management in Situation-Specific Network Construction
This paper considers the problem of knowledgebased model construction in the presence of uncertainty about the association of domain entities to random variables. Multi-entity Bay...
Kathryn B. Laskey, Suzanne M. Mahoney, Ed Wright
ICML
2010
IEEE
15 years 2 months ago
Restricted Boltzmann Machines are Hard to Approximately Evaluate or Simulate
Restricted Boltzmann Machines (RBMs) are a type of probability model over the Boolean cube {-1, 1}n that have recently received much attention. We establish the intractability of ...
Philip M. Long, Rocco A. Servedio
JAIR
2006
160views more  JAIR 2006»
15 years 1 months ago
Anytime Point-Based Approximations for Large POMDPs
The Partially Observable Markov Decision Process has long been recognized as a rich framework for real-world planning and control problems, especially in robotics. However exact s...
Joelle Pineau, Geoffrey J. Gordon, Sebastian Thrun