Sciweavers

990 search results - page 51 / 198
» Using evolution strategies to solve DEC-POMDP problems
Sort
View
GECCO
2008
Springer
129views Optimization» more  GECCO 2008»
13 years 9 months ago
Exploiting the path of least resistance in evolution
Hereditary Repulsion (HR) is a selection method coupled with a fitness constraint that substantially improves the performance and consistency of evolutionary algorithms. This als...
Gearoid Murphy, Conor Ryan
GECCO
2011
Springer
276views Optimization» more  GECCO 2011»
12 years 11 months ago
Evolution of reward functions for reinforcement learning
The reward functions that drive reinforcement learning systems are generally derived directly from the descriptions of the problems that the systems are being used to solve. In so...
Scott Niekum, Lee Spector, Andrew G. Barto
AIMSA
2008
Springer
14 years 2 months ago
Incorporating Learning in Grid-Based Randomized SAT Solving
Abstract. Computational Grids provide a widely distributed computing environment suitable for randomized SAT solving. This paper develops techniques for incorporating learning, kno...
Antti Eero Johannes Hyvärinen, Tommi A. Juntt...
TROB
2008
112views more  TROB 2008»
13 years 8 months ago
A Complete and Scalable Strategy for Coordinating Multiple Robots Within Roadmaps
Abstract--This paper addresses the challenging problem of finding collision-free trajectories for many robots moving toward individual goals within a common environment. Most popul...
Mike Peasgood, Christopher M. Clark, John McPhee
GECCO
2009
Springer
103views Optimization» more  GECCO 2009»
14 years 2 months ago
Why evolution is not a good paradigm for program induction: a critique of genetic programming
We revisit the roots of Genetic Programming (i.e. Natural Evolution), and conclude that the mechanisms of the process of evolution (i.e. selection, inheritance and variation) are ...
John R. Woodward, Ruibin Bai