Sciweavers

236 search results - page 38 / 48
» Bias and Variance Approximation in Value Function Estimates
Sort
View
JAIR
2002
163views more  JAIR 2002»
13 years 8 months ago
Efficient Reinforcement Learning Using Recursive Least-Squares Methods
The recursive least-squares (RLS) algorithm is one of the most well-known algorithms used in adaptive filtering, system identification and adaptive control. Its popularity is main...
Xin Xu, Hangen He, Dewen Hu
ICML
2008
IEEE
14 years 9 months ago
Sample-based learning and search with permanent and transient memories
We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...
David Silver, Martin Müller 0003, Richard S. ...
SIAMCOMP
2010
174views more  SIAMCOMP 2010»
13 years 7 months ago
On the Complexity of Nash Equilibria and Other Fixed Points
We reexamine what it means to compute Nash equilibria and, more generally, what it means to compute a fixed point of a given Brouwer function, and we investigate the complexity o...
Kousha Etessami, Mihalis Yannakakis
EC
2011
240views ECommerce» more  EC 2011»
13 years 3 months ago
HypE: An Algorithm for Fast Hypervolume-Based Many-Objective Optimization
Abstract—In the field of evolutionary multi-criterion optimization, the hypervolume indicator is the only single set quality measure that is known to be strictly monotonic with ...
Johannes Bader, Eckart Zitzler
ICIP
2000
IEEE
14 years 10 months ago
Statistical Threshold Design for the Two-State Signal-Dependent Rank Order Mean Filter
The signal-dependent rank order mean (SD-ROM) ?lter is effective at removing high levels of impulse noise from 2D scalar-valued signals. Excellent results have been presented for ...
Michael S. Moore, Sanjit K. Mitra