Sciweavers

369 search results - page 28 / 74
» Global Optimization for Value Function Approximation
Sort
View
JAIR
2006
122views more  JAIR 2006»
14 years 11 months ago
Solving Factored MDPs with Hybrid State and Action Variables
Efficient representations and solutions for large decision problems with continuous and discrete variables are among the most important challenges faced by the designers of automa...
Branislav Kveton, Milos Hauskrecht, Carlos Guestri...
AUTOMATICA
2007
179views more  AUTOMATICA 2007»
14 years 12 months ago
Approximate bisimulation relations for constrained linear systems
In this paper, we define the notion of approximate bisimulation relation between two continuous systems. While exact bisimulation requires that the observations of two systems ar...
Antoine Girard, George J. Pappas
WSC
2004
15 years 1 months ago
Efficient Simulation-Based Discrete Optimization
In many practical applications of simulation it is desirable to optimize the levels of integer or binary variables that are inputs for the simulation model. In these cases, the ob...
Seth D. Guikema, Rachel A. Davidson, Zehra Ç...
ATAL
2008
Springer
15 years 1 months ago
Transfer of task representation in reinforcement learning using policy-based proto-value functions
Reinforcement Learning research is traditionally devoted to solve single-task problems. Therefore, anytime a new task is faced, learning must be restarted from scratch. Recently, ...
Eliseo Ferrante, Alessandro Lazaric, Marcello Rest...
CISS
2008
IEEE
15 years 6 months ago
Subgradient methods in network resource allocation: Rate analysis
— We consider dual subgradient methods for solving (nonsmooth) convex constrained optimization problems. Our focus is on generating approximate primal solutions with performance ...
Angelia Nedic, Asuman E. Ozdaglar