Sciweavers

178 search results - page 7 / 36
» Efficient Approximation of Optimal Control for Markov Games
Sort
View
108
Voted
JAIR
2002
163views more  JAIR 2002»
14 years 9 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
GECCO
2007
Springer
210views Optimization» more  GECCO 2007»
15 years 3 months ago
Markov chain models of bare-bones particle swarm optimizers
We apply a novel theoretical approach to better understand the behaviour of different types of bare-bones PSOs. It avoids many common but unrealistic assumptions often used in an...
Riccardo Poli, William B. Langdon
NN
2010
Springer
187views Neural Networks» more  NN 2010»
14 years 4 months ago
Efficient exploration through active learning for value function approximation in reinforcement learning
Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares ...
Takayuki Akiyama, Hirotaka Hachiya, Masashi Sugiya...
STOC
2007
ACM
146views Algorithms» more  STOC 2007»
15 years 9 months ago
Playing games with approximation algorithms
In an online linear optimization problem, on each period t, an online algorithm chooses st S from a fixed (possibly infinite) set S of feasible decisions. Nature (who may be adve...
Sham M. Kakade, Adam Tauman Kalai, Katrina Ligett
MOC
2000
76views more  MOC 2000»
14 years 9 months ago
Optimal approximation of stochastic differential equations by adaptive step-size control
We study the pathwise (strong) approximation of scalar stochastic differential equations with respect to the global error in the L2-norm. For equations with additive noise we estab...
Norbert Hofmann, Thomas Müller-Gronbach, Klau...