Sciweavers

162 search results - page 18 / 33
» Topological Value Iteration Algorithm for Markov Decision Pr...
Sort
View
NIPS
2004
14 years 11 months ago
A Cost-Shaping LP for Bellman Error Minimization with Performance Guarantees
We introduce a new algorithm based on linear programming that approximates the differential value function of an average-cost Markov decision process via a linear combination of p...
Daniela Pucci de Farias, Benjamin Van Roy
AAAI
2007
15 years 6 days ago
Compact Spectral Bases for Value Function Approximation Using Kronecker Factorization
A new spectral approach to value function approximation has recently been proposed to automatically construct basis functions from samples. Global basis functions called proto-val...
Jeffrey Johns, Sridhar Mahadevan, Chang Wang

Publication
233views
13 years 8 months ago
Sparse reward processes
We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained duri...
Christos Dimitrakakis
ICML
2003
IEEE
15 years 10 months ago
Planning in the Presence of Cost Functions Controlled by an Adversary
We investigate methods for planning in a Markov Decision Process where the cost function is chosen by an adversary after we fix our policy. As a running example, we consider a rob...
H. Brendan McMahan, Geoffrey J. Gordon, Avrim Blum
DMKD
2004
ACM
139views Data Mining» more  DMKD 2004»
15 years 3 months ago
Iterative record linkage for cleaning and integration
Record linkage, the problem of determining when two records refer to the same entity, has applications for both data cleaning (deduplication) and for integrating data from multipl...
Indrajit Bhattacharya, Lise Getoor