Sciweavers

297 search results - page 38 / 60
» J-MADeM, a market-based model for complex decision problems
Sort
View
AIEDAM
2008
127views more  AIEDAM 2008»
13 years 8 months ago
Evolving blackbox quantum algorithms using genetic programming
Although it is known that quantum computers can solve certain computational problems exponentially faster than classical computers, only a small number of quantum algorithms have ...
Ralf Stadelhofer, Wolfgang Banzhaf, Dieter Suter
ATAL
2009
Springer
14 years 3 months ago
Constraint-based dynamic programming for decentralized POMDPs with structured interactions
Decentralized partially observable MDPs (DEC-POMDPs) provide a rich framework for modeling decision making by a team of agents. Despite rapid progress in this area, the limited sc...
Akshat Kumar, Shlomo Zilberstein
ICML
2001
IEEE
14 years 9 months ago
Continuous-Time Hierarchical Reinforcement Learning
Hierarchical reinforcement learning (RL) is a general framework which studies how to exploit the structure of actions and tasks to accelerate policy learning in large domains. Pri...
Mohammad Ghavamzadeh, Sridhar Mahadevan
RTSS
2002
IEEE
14 years 1 months ago
Approximate Schedulability Analysis
The schedulability analysis problem for many realistic task models is intractable. Therefore known algorithms either have exponential complexity or at best can be solved in pseudo...
Samarjit Chakraborty, Simon Künzli, Lothar Th...
ATAL
2008
Springer
13 years 10 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