Sciweavers

4843 search results - page 342 / 969
» The Shortcut Problem - Complexity and Approximation
Sort
View
CCIA
2005
Springer
15 years 9 months ago
Direct Policy Search Reinforcement Learning for Robot Control
— This paper proposes a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, whe...
Andres El-Fakdi, Marc Carreras, Narcís Palo...
ICALP
2005
Springer
15 years 9 months ago
Decidability in Syntactic Control of Interference
We investigate the decidability of observational equivalence and approximation in “Syntactic Control of Interference” (SCI). By asg denotations of terms in an inequationally fu...
James Laird
CDC
2009
IEEE
173views Control Systems» more  CDC 2009»
15 years 9 months ago
A contractivity approach for probabilistic bisimulations of diffusion processes
— This work is concerned with the problem of characterizing and computing probabilistic bisimulations of diffusion processes. A probabilistic bisimulation relation between two su...
Alessandro Abate
NIPS
2008
15 years 5 months ago
Bayesian Experimental Design of Magnetic Resonance Imaging Sequences
We show how improved sequences for magnetic resonance imaging can be found through optimization of Bayesian design scores. Combining approximate Bayesian inference and natural ima...
Matthias W. Seeger, Hannes Nickisch, Rolf Pohmann,...
AIPS
2006
15 years 5 months ago
Solving Factored MDPs with Exponential-Family Transition Models
Markov decision processes (MDPs) with discrete and continuous state and action components can be solved efficiently by hybrid approximate linear programming (HALP). The main idea ...
Branislav Kveton, Milos Hauskrecht