Sciweavers

3694 search results - page 8 / 739
» Stochastic complexity in learning
Sort
View
AIPS
2006
13 years 9 months ago
Combining Stochastic Task Models with Reinforcement Learning for Dynamic Scheduling
We view dynamic scheduling as a sequential decision problem. Firstly, we introduce a generalized planning operator, the stochastic task model (STM), which predicts the effects of ...
Malcolm J. A. Strens
CPE
2003
Springer
149views Hardware» more  CPE 2003»
14 years 21 days ago
Logical and Stochastic Modeling with SMART
We describe the main features of SmArT, a software package providing a seamless environment for the logic and probabilistic analysis of complex systems. SmArT can combine differen...
Gianfranco Ciardo, R. L. Jones III, Andrew S. Mine...
ATAL
2008
Springer
13 years 9 months ago
An approach to online optimization of heuristic coordination algorithms
Due to computational intractability, large scale coordination algorithms are necessarily heuristic and hence require tuning for particular environments. In domains where character...
Jumpol Polvichai, Paul Scerri, Michael Lewis
ISAAC
2009
Springer
169views Algorithms» more  ISAAC 2009»
14 years 2 months ago
The Complexity of Solving Stochastic Games on Graphs
We consider some well-known families of two-player zero-sum perfect-information stochastic games played on finite directed graphs. Generalizing and unifying results of Liggett and...
Daniel Andersson, Peter Bro Miltersen
ICML
2009
IEEE
14 years 8 months ago
Robot trajectory optimization using approximate inference
The general stochastic optimal control (SOC) problem in robotics scenarios is often too complex to be solved exactly and in near real time. A classical approximate solution is to ...
Marc Toussaint