An apparatus for generating patterned images which are variable in color contrast and spatial frequency while retaining a substantially constant, uniform level of photometric luminance. Two broad spectrum beams of luminous energy are individually projected through two orthogonally oriented polarizers and interleaved upon being split. The intensity in one beam is homogeneous while the other contains a spatially periodic pattern. The two beams created by splitting and interleaving are selectively color filtered and combined after one is translated sufficiently to reverse its phase relative to the other. A rotating polarizer in the path of the output combined beam alters the pattern color composition between one extreme where the spatially reversing colors are defined by the color filters and the opposite extreme in which the pattern disappears into a uniform composition of the two colors.
[1]
Andrew G. Barto,et al.
Improving Elevator Performance Using Reinforcement Learning
,
1995,
NIPS.
[2]
Andrew G. Barto,et al.
Learning to Act Using Real-Time Dynamic Programming
,
1995,
Artif. Intell..
[3]
Martin A. Riedmiller.
Learning to Control Dynamic Systems
,
1996
.
[4]
Wei Zhang,et al.
A Reinforcement Learning Approach to job-shop Scheduling
,
1995,
IJCAI.
[5]
Richard S. Sutton,et al.
Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding
,
1995,
NIPS.