Sciweavers

135 search results - page 25 / 27
» Dynamic Workflow Composition using Markov Decision Processes
Sort
View
ICML
1996
IEEE
13 years 12 months ago
A Convergent Reinforcement Learning Algorithm in the Continuous Case: The Finite-Element Reinforcement Learning
This paper presents a direct reinforcement learning algorithm, called Finite-Element Reinforcement Learning, in the continuous case, i.e. continuous state-space and time. The eval...
Rémi Munos
AAAI
2007
13 years 10 months ago
Authorial Idioms for Target Distributions in TTD-MDPs
In designing Markov Decision Processes (MDP), one must define the world, its dynamics, a set of actions, and a reward function. MDPs are often applied in situations where there i...
David L. Roberts, Sooraj Bhat, Kenneth St. Clair, ...
AUTOMATICA
2007
124views more  AUTOMATICA 2007»
13 years 7 months ago
Motion planning in uncertain environments with vision-like sensors
In this work we present a methodology for intelligent path planning in an uncertain environment using vision like sensors, i.e., sensors that allow the sensing of the environment ...
Suman Chakravorty, John L. Junkins
JMLR
2006
190views more  JMLR 2006»
13 years 7 months ago
Causal Graph Based Decomposition of Factored MDPs
We present Variable Influence Structure Analysis, or VISA, an algorithm that performs hierarchical decomposition of factored Markov decision processes. VISA uses a dynamic Bayesia...
Anders Jonsson, Andrew G. Barto
GLOBECOM
2010
IEEE
13 years 5 months ago
Need-Based Communication for Smart Grid: When to Inquire Power Price?
In smart grid, a home appliance can adjust its power consumption level according to the realtime power price obtained from communication channels. Most studies on smart grid do not...
Husheng Li, Robert C. Qiu