Sciweavers

682 search results - page 88 / 137
» One-Counter Markov Decision Processes
Sort
View
111
Voted
DIALM
2000
ACM
112views Algorithms» more  DIALM 2000»
15 years 5 months ago
A decision-theoretic approach to resource allocation in wireless multimedia networks
The allocation of scarce spectral resources to support as many user applications as possible while maintaining reasonable quality of service is a fundamental problem in wireless c...
Zygmunt J. Haas, Joseph Y. Halpern, Erran L. Li, S...
92
Voted
AAAI
2007
15 years 3 months ago
Optimizing Anthrax Outbreak Detection Using Reinforcement Learning
The potentially catastrophic impact of a bioterrorist attack makes developing effective detection methods essential for public health. In the case of anthrax attack, a delay of ho...
Masoumeh T. Izadi, David L. Buckeridge
103
Voted
AAAI
2010
15 years 2 months ago
Robust Policy Computation in Reward-Uncertain MDPs Using Nondominated Policies
The precise specification of reward functions for Markov decision processes (MDPs) is often extremely difficult, motivating research into both reward elicitation and the robust so...
Kevin Regan, Craig Boutilier
IJCAI
2001
15 years 2 months ago
Complexity of Probabilistic Planning under Average Rewards
A general and expressive model of sequential decision making under uncertainty is provided by the Markov decision processes (MDPs) framework. Complex applications with very large ...
Jussi Rintanen
MOR
2008
87views more  MOR 2008»
15 years 23 days ago
On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP
We consider the average cost problem for partially observable Markov decision processes (POMDP) with finite state, observation, and control spaces. We prove that there exists an -...
Huizhen Yu, Dimitri P. Bertsekas