1974 search results - page 61 / 395 » On Unbiased Linear Approximations |
94
Voted
NIPS
2001
15 years 2 months ago
2001
We address two open theoretical questions in Policy Gradient Reinforcement Learning. The first concerns the efficacy of using function approximation to represent the state action ...
64
Voted
MOC
1998
15 years 8 days ago
1998
Abstract. We present formulations of the Trotter-Kato theorem for approximation of linear C0-semigroups which provide very useful framework when convergence of numerical approximat...
104
click to vote
JAIR
2006
15 years 17 days ago
2006
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...
CAGD
1999
15 years 8 days ago
1999
By its dual representation, a developable surface can be viewed as a curve of dual projective 3-space. After introducing an appropriate metric in the dual space and restricting ou...
109
click to vote
STOC
2007
ACM
16 years 27 days ago
2007
ACM
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...