Efficient Algorithm for Reinforcement Learning with Partial Variation

This paper presents reinforcement learning (RL) algorithm for routing strategy considering the state of network link, which can be deemed as a dynamic programming problem with stochastic needs. Through modeling those four elements and experiments, we draw the conclusion that upon the state of network link, RL is an efficient algorithm for routing strategy; the data can be efficient forwarded to the destination.

Download Full-text

Selecting an efficient algorithm for Adhoc network routing using multi-criteria choice in algorithms based on reinforcement learning and network traffic

International Journal of Academic Research ◽

10.7813/2075-4124.2012/4-5/a.6 ◽

2012 ◽

Vol 4 (5) ◽

pp. 66-73

Author(s):

Robabeh Chanpa ◽

Leila Yahyayi

Keyword(s):

Reinforcement Learning ◽

Network Traffic ◽

Efficient Algorithm ◽

Network Routing ◽

Adhoc Network

Download Full-text

REINFORCEMENT LEARNING WITH GOAL-DIRECTED ELIGIBILITY TRACES

International Journal of Modern Physics C ◽

10.1142/s0129183104006662 ◽

2004 ◽

Vol 15 (09) ◽

pp. 1235-1247 ◽

Cited By ~ 1

Author(s):

M. ANDRECUT ◽

M. K. ALI

Keyword(s):

Reinforcement Learning ◽

Efficient Algorithm ◽

Learning Problem ◽

Delayed Reward ◽

Eligibility Trace

The eligibility trace is the most important mechanism used so far in reinforcement learning to handle delayed reward. Here, we introduce a new kind of eligibility trace, the goal-directed trace, and show that it results in more reliable learning than the conventional trace. In addition, we also propose a new efficient algorithm for solving the goal-directed reinforcement learning problem.

Download Full-text

Computational Micrograph Registration with Sieve Processes

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100164660 ◽

1996 ◽

Vol 54 ◽

pp. 440-441

Author(s):

P.J. Phillips ◽

J. Huang ◽

S. M. Dunn

Keyword(s):

Planar Graph ◽

Efficient Algorithm ◽

Spatial Organization ◽

Spatial Arrangement ◽

Stereo Image ◽

Image Model ◽

Geometric Invariants ◽

Point Set

In this paper we present an efficient algorithm for automatically finding the correspondence between pairs of stereo micrographs, the key step in forming a stereo image. The computation burden in this problem is solving for the optimal mapping and transformation between the two micrographs. In this paper, we present a sieve algorithm for efficiently estimating the transformation and correspondence.In a sieve algorithm, a sequence of stages gradually reduce the number of transformations and correspondences that need to be examined, i.e., the analogy of sieving through the set of mappings with gradually finer meshes until the answer is found. The set of sieves is derived from an image model, here a planar graph that encodes the spatial organization of the features. In the sieve algorithm, the graph represents the spatial arrangement of objects in the image. The algorithm for finding the correspondence restricts its attention to the graph, with the correspondence being found by a combination of graph matchings, point set matching and geometric invariants.

Download Full-text