Sciweavers

107 search results - page 5 / 22
» Approximate Linear Programming for Constrained Partially Obs...
Sort
View
AAAI
2007
13 years 9 months ago
Purely Epistemic Markov Decision Processes
Planning under uncertainty involves two distinct sources of uncertainty: uncertainty about the effects of actions and uncertainty about the current state of the world. The most wi...
Régis Sabbadin, Jérôme Lang, N...
GLOBECOM
2007
IEEE
13 years 11 months ago
Bursty Traffic in Energy-Constrained Opportunistic Spectrum Access
We design opportunistic spectrum access strategies for improving spectrum efficiency. In each slot, a secondary user chooses a subset of channels to sense and decides whether to ac...
Yunxia Chen, Qing Zhao, Ananthram Swami
COLT
2000
Springer
13 years 11 months ago
Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process (  ¢¡¤£¦¥§  ), and focus on gradient ascent approache...
Peter L. Bartlett, Jonathan Baxter
AAAI
2011
12 years 7 months ago
Linear Dynamic Programs for Resource Management
Sustainable resource management in many domains presents large continuous stochastic optimization problems, which can often be modeled as Markov decision processes (MDPs). To solv...
Marek Petrik, Shlomo Zilberstein
AAAI
2010
13 years 9 months ago
Relational Partially Observable MDPs
Relational Markov Decision Processes (MDP) are a useraction for stochastic planning problems since one can develop abstract solutions for them that are independent of domain size ...
Chenggang Wang, Roni Khardon