Sciweavers

334 search results - page 31 / 67
» How to Dynamically Merge Markov Decision Processes
Sort
View
NIPS
2007
14 years 11 months ago
Online Linear Regression and Its Application to Model-Based Reinforcement Learning
We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a mo...
Alexander L. Strehl, Michael L. Littman
IM
2003
14 years 11 months ago
A Revenue-based Model for Making Resource Investment Decisions in IP Networks
: Capacity planning is a critical task in network management. It identifies how much capacity is needed to match future traffic demand. It directly affects customer satisfaction ...
Srinivasan Jagannathan, Jörn Altmann, Lee Rho...
AAAI
2010
14 years 11 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
PE
2010
Springer
123views Optimization» more  PE 2010»
14 years 4 months ago
Evaluating fluid semantics for passive stochastic process algebra cooperation
Fluid modelling is a next-generation technique for analysing massive performance models. Passive cooperation is a popular cooperation mechanism frequently used by performance engi...
Richard A. Hayden, Jeremy T. Bradley
AAAI
2012
13 years 1 days ago
A Dynamic Rationalization of Distance Rationalizability
Distance rationalizability is an intuitive paradigm for developing and studying voting rules: given a notion of consensus and a distance function on preference profiles, a ration...
Craig Boutilier, Ariel D. Procaccia