1506 search results - page 145 / 302 » On the Distribution of Natural Probability Functions |
143
click to vote
IJCAI
2003
15 years 6 months ago
2003
We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geom...
143
click to vote
NCA
2006
IEEE
15 years 4 months ago
2006
IEEE
The goal of this paper is to design a new control algorithm for open-loop control of complex systems. This control approach is based on a genealogical decision tree for both regula...
117
click to vote
CORR
2010
Springer
15 years 4 months ago
2010
Springer
We consider a dense n-user Gaussian interference network formed by paired transmitters and receivers placed independently at random in Euclidean space. Under natural conditions on ...
166
click to vote
INFOCOM
2010
IEEE
15 years 3 months ago
2010
IEEE
In this paper we show that complex (scale-free) network topologies naturally emerge from hyperbolic metric spaces. The hyperbolic geometry can be used to facilitate maximally efï¬...
161
click to vote
TFS
2011
14 years 11 months ago
2011
—Reinforcement learning (RL) is a valuable learning method when the systems require a selection of control actions whose consequences emerge over long periods for which input– ...