Results 1  10
of
173
Efficient Reinforcement Learning through Symbiotic Evolution
 Machine Learning
, 1996
"... . This article presents a new reinforcement learning method called SANE (Symbiotic, Adaptive NeuroEvolution), which evolves a population of neurons through genetic algorithms to form a neural network capable of performing a task. Symbiotic evolution promotes both cooperation and specialization, whi ..."
Abstract

Cited by 132 (37 self)
 Add to MetaCart
. This article presents a new reinforcement learning method called SANE (Symbiotic, Adaptive NeuroEvolution), which evolves a population of neurons through genetic algorithms to form a neural network capable of performing a task. Symbiotic evolution promotes both cooperation and specialization, which results in a fast, efficient genetic search and discourages convergence to suboptimal solutions. In the inverted pendulum problem, SANE formed effective networks 9 to 16 times faster than the Adaptive Heuristic Critic and 2 times faster than Q learning and the GENITOR neuroevolution approachwithout loss of generalization. Such efficient learning, combined with few domain assumptions, make SANE a promising approach to a broad range of reinforcement learning problems, including many realworld applications. Keywords: NeuroEvolution, Reinforcement Learning, Genetic Algorithms, Neural Networks. 1. Introduction Learning effective decision policies is a difficult problem that appears in m...
Evaluating Evolutionary Algorithms
 Artificial Intelligence
, 1996
"... Test functions are commonly used to evaluate the effectiveness of different search algorithms. However, the results of evaluation are as dependent on the test problems as they are on the algorithms that are the subject of comparison. Unfortunately, developing a test suite for evaluating competing se ..."
Abstract

Cited by 86 (14 self)
 Add to MetaCart
Test functions are commonly used to evaluate the effectiveness of different search algorithms. However, the results of evaluation are as dependent on the test problems as they are on the algorithms that are the subject of comparison. Unfortunately, developing a test suite for evaluating competing search algorithms is difficult without clearly defined evaluation goals. In this paper we discuss some basic principles that can be used to develop test suites and we examine the role of test suites as they have been used to evaluate evolutionary search algorithms. Current test suites include functions that are easily solved by simple search methods such as greedy hillclimbers. Some test functions also have undesirable characteristics that are exaggerated as the dimensionality of the search space is increased. New methods are examined for constructing functions with different degrees of nonlinearity, where the interactions and the cost of evaluation scale with respect to the dimensionality of...
Adding learning to the cellular development of neural networks: Evolution and the Baldwin effect.
 Evolutionary Computation
, 1993
"... A grammar tree is used to encode a cellular developmental process that can generate whole families of Boolean neural networks for computing parity and symmetry. The development process resembles biological cell division. A genetic algorithm is used to find a grammar tree that yields both architec ..."
Abstract

Cited by 77 (2 self)
 Add to MetaCart
A grammar tree is used to encode a cellular developmental process that can generate whole families of Boolean neural networks for computing parity and symmetry. The development process resembles biological cell division. A genetic algorithm is used to find a grammar tree that yields both architecture and weights specifying a particular neural network for solving specific Boolean functions. The current study particularly focuses on the addition of learning to the development process and the evolution of grammar trees. Three ways of adding learning to development process are explored. Two of these exploit the Baldwin effect by changing the fitness landscape without using Lamarckian evolution. The third strategy is Lamarckian in nature. Results for these three modes of combining learning with genetic search are compared against genetic search without learning. Our results suggest that merely using learning to change the fitness landscape can be as effective as Lamarckian strate...
Schema Theory for Genetic Programming with Onepoint Crossover and Point Mutation
 Evolutionary Computation
, 1998
"... We review the main results obtained in the theory of schemata in Genetic Programming (GP) emphasising their strengths and weaknesses. Then we propose a new, simpler definition of the concept of schema for GP which is closer to the original concept of schema in genetic algorithms (GAs). Along with ..."
Abstract

Cited by 60 (30 self)
 Add to MetaCart
We review the main results obtained in the theory of schemata in Genetic Programming (GP) emphasising their strengths and weaknesses. Then we propose a new, simpler definition of the concept of schema for GP which is closer to the original concept of schema in genetic algorithms (GAs). Along with a new form of crossover, onepoint crossover, and point mutation this concept of schema has been used to derive an improved schema theorem for GP which describes the propagation of schemata from one generation to the next. We discuss this result and show that our schema theorem is the natural counterpart for GP of the schema theorem for GAs, to which it asymptotically converges. 1 Introduction Genetic Programming (GP) has been applied successfully to a large number of difficult problems like automatic design, pattern recognition, robotic control, synthesis on neural architectures, symbolic regression, music and picture generation [2, 9, 10, 11, 12, 13]. However a relatively small numbe...
SearchBased Software Engineering
"... ... The paper briefly sets out key ingredients for successful reformulation and evaluation criteria for SearchBased Software Engineering. ..."
Abstract

Cited by 60 (2 self)
 Add to MetaCart
... The paper briefly sets out key ingredients for successful reformulation and evaluation criteria for SearchBased Software Engineering.
Using modern graphics architectures for generalpurpose computing: A framework and analysis
, 2002
"... Recently, graphics hardware architectures have begun to emphasize versatility, offering rich new ways to programmatically reconfigure the graphics pipeline. In this paper, we explore whether current graphics architectures can be applied to problems where generalpurpose vector processors might tradi ..."
Abstract

Cited by 58 (0 self)
 Add to MetaCart
Recently, graphics hardware architectures have begun to emphasize versatility, offering rich new ways to programmatically reconfigure the graphics pipeline. In this paper, we explore whether current graphics architectures can be applied to problems where generalpurpose vector processors might traditionally be used. We develop a programming framework and apply it to a variety of problems, including matrix multiplication and 3SAT. Comparing the speed of our graphics card implementations to standard CPU implementations, we demonstrate startling performance improvements in many cases, as well as room for improvement in others. We analyze the bottlenecks and propose minor extensions to current graphics architectures which would improve their effectiveness for solving generalpurpose problems. Based on our results and current trends in microarchitecture, we believe that efficient use of graphics hardware will become increasingly important to highperformance computing on commodity hardware. 1.
Comparison of resampling schemes for particle filtering
 In 4th International Symposium on Image and Signal Processing and Analysis (ISPA
, 2005
"... douc atcmapx.polytechnique.fr This contribution is devoted to the comparison of various resampling approaches that have been proposed in the literature on particle filtering. It is first shown using simple arguments that the socalled residual and stratified methods do yield an improvement over the ..."
Abstract

Cited by 55 (0 self)
 Add to MetaCart
douc atcmapx.polytechnique.fr This contribution is devoted to the comparison of various resampling approaches that have been proposed in the literature on particle filtering. It is first shown using simple arguments that the socalled residual and stratified methods do yield an improvement over the basic multinomial resampling approach. A simple counterexample showing that this property does not hold true for systematic resampling is given. Finally, some results on the largesample behavior of the simple bootstrap filter algorithm are given. In particular, a central limit theorem is established for the case where resampling is performed using the residual approach. 1
A New Schema Theory for Genetic Programming with Onepoint Crossover and Point Mutation
 Genetic Programming 1997: Proceedings of the Second Annual Conference
, 1997
"... In this paper we first review the main results obtained in the theory of schemata in Genetic Programming (GP) emphasising their strengths and weaknesses. Then we propose a new, simpler definition of the concept of schema for GP which is quite close to the original concept of schema in genetic ..."
Abstract

Cited by 55 (36 self)
 Add to MetaCart
In this paper we first review the main results obtained in the theory of schemata in Genetic Programming (GP) emphasising their strengths and weaknesses. Then we propose a new, simpler definition of the concept of schema for GP which is quite close to the original concept of schema in genetic algorithms (GAs).
General Schema Theory for Genetic Programming with SubtreeSwapping Crossover
 In Genetic Programming, Proceedings of EuroGP 2001, LNCS
, 2001
"... In this paper a new, general and exact schema theory for genetic programming is presented. The theory includes a microscopic schema theorem applicable to crossover operators which replace a subtree in one parent with a subtree from the other parent to produce the offspring. A more macroscopic schema ..."
Abstract

Cited by 45 (28 self)
 Add to MetaCart
In this paper a new, general and exact schema theory for genetic programming is presented. The theory includes a microscopic schema theorem applicable to crossover operators which replace a subtree in one parent with a subtree from the other parent to produce the offspring. A more macroscopic schema theorem is also provided which is valid for crossover operators in which the probability of selecting any two crossover points in the parents depends only on their size and shape. The theory is based on the notions of Cartesian node reference systems and variablearity hyperschemata both introduced here for the first time. In the paper we provide examples which show how the theory can be specialised to specific crossover operators and how it can be used to derive an exact definition of effective fitness and a sizeevolution equation for GP. 1