Results 1  10
of
22
Evolutionary Algorithms for Reinforcement Learning
 Journal of Artificial Intelligence Research
, 1999
"... There are two distinct approaches to solving reinforcement learning problems, namely, searching in value function space and searching in policy space. Temporal difference methods and evolutionary algorithms are wellknown examples of these approaches. Kaelbling, Littman and Moore recently provided a ..."
Abstract

Cited by 83 (1 self)
 Add to MetaCart
There are two distinct approaches to solving reinforcement learning problems, namely, searching in value function space and searching in policy space. Temporal difference methods and evolutionary algorithms are wellknown examples of these approaches. Kaelbling, Littman and Moore recently provided an informative survey of temporal difference methods. This article focuses on the application of evolutionary algorithms to the reinforcement learning problem, emphasizing alternative policy representations, credit assignment methods, and problemspecific genetic operators. Strengths and weaknesses of the evolutionary approach to reinforcement learning are presented, along with a survey of representative applications. 1. Introduction Kaelbling, Littman, and Moore (1996) and more recently Sutton and Barto (1998) provide informative surveys of the field of reinforcement learning (RL). They characterize two classes of methods for reinforcement learning: methods that search the space of value fu...
Combinatorial Landscapes
 SIAM REVIEW
, 2002
"... Fitness landscapes have proven to be a valuable concept in evolutionary biology, combinatorial optimization, and the physics of disordered systems. A fitness landscape is a mapping from a configuration space into the real numbers. The configuration space is equipped with some notion of adjacency, ne ..."
Abstract

Cited by 33 (2 self)
 Add to MetaCart
Fitness landscapes have proven to be a valuable concept in evolutionary biology, combinatorial optimization, and the physics of disordered systems. A fitness landscape is a mapping from a configuration space into the real numbers. The configuration space is equipped with some notion of adjacency, nearness, distance or accessibility. Landscape theory has emerged as an attempt to devise suitable mathematical structures for describing the "static" properties of landscapes as well as their influence on the dynamics of adaptation. In this review we focus on the connections of landscape theory with algebraic combinatorics and random graph theory, where exact results are available.
Toward a Unified Theory of Learning: Multistrategy TaskAdaptive Learning
 IN: READINGS IN KNOWLEDGE ACQUISITION AND
, 1993
"... Any learning process can be viewed as a selfmodification of the leaxnefs current knowledge tArough an. interaction with some information source. Such knowledge modification is guided by the learner's deshe to achieve a certain outcome, and can engage any kind of inference. The type of inference inv ..."
Abstract

Cited by 29 (10 self)
 Add to MetaCart
Any learning process can be viewed as a selfmodification of the leaxnefs current knowledge tArough an. interaction with some information source. Such knowledge modification is guided by the learner's deshe to achieve a certain outcome, and can engage any kind of inference. The type of inference involved depends on he input information, the current (background) knowledge and the learneFs task ax hand. Based on such a view of learning, several fundamental concepts are analized and clarified, in paxticular, analytic and synthetic learning, derivm:ional and hypothetical explanation, constnictive induction, abduction, abstraction and deductive generalization. It is shown that inductive generalization and abduction can be viewed as two basic forms of general induction, and that abstraction and deductive generalization axe two related forms of constructive deduction. Using this conceptual framework, a methodology for multistrategy taskadaptive learning (MTL) is outlined, in which learning strategies axe combined dynamically, depending on the current learning situation. Speccally, an MTL learner anaLizes a "wiad" relationship among the input information, the background knowledge and the learning task, and on that basis determines which strategy, or. a combination thereof, is most appropriate at a given learning step. To implement the MTL methodology, a new knowledge representation is proposed, based on the parametric association rules (PARs). Basic ideas of MTL are illustrated by means of the wellknown "cup" example, through which is shown how an MTL learner can employ, depending the above mad relationship, emprical learning, constructive inductive generalization, abduction, explanationbased learning and absuaction.
The algebraic theory of recombination spaces
, 2000
"... A new mathematical representation is proposed for the configuration space structure induced by recombination which we called "Pstructure". It consists of a mapping of pairs of objects to the power set of all objects in the search space. The mapping assigns to each pair of parental "genotypes" the s ..."
Abstract

Cited by 29 (15 self)
 Add to MetaCart
A new mathematical representation is proposed for the configuration space structure induced by recombination which we called "Pstructure". It consists of a mapping of pairs of objects to the power set of all objects in the search space. The mapping assigns to each pair of parental "genotypes" the set of all recombinant genotypes obtainable from the parental ones. It is shown that this construction allows a Fourierdecomposition of fitness landscapes into a superposition of "elementary landscapes". This decomposition is analogous to the Fourier decomposition of fitness landscapes on mutation spaces. The elementary landscapes are obtained as eigenfunctions of a Laplacian operator defined for Pstructures. For binary string recombination the elementary landscapes are exactly the pspin functions (Walsh functions), i.e. the same as the elementary landscapes of the string point mutation spaces (i.e. the hypercube). This supports the notion of a strong homomorphisms between string mutation ...
A genetic algorithm for multiple molecular sequence alignment
 Comput Appl Biosci
, 1997
"... Motivation: Multiple molecular sequence alignment is among the most important and most challenging tasks in computational biology. The currently used alignment techniques are characterized by great computational complexity, which prevents their wider use. This research is aimed at developing a new t ..."
Abstract

Cited by 19 (0 self)
 Add to MetaCart
Motivation: Multiple molecular sequence alignment is among the most important and most challenging tasks in computational biology. The currently used alignment techniques are characterized by great computational complexity, which prevents their wider use. This research is aimed at developing a new technique for efficient multiple sequence alignment. Approach: The new method is based on genetic algorithms. Genetic algorithms are stochastic approaches for efficient and robust searching. By converting biomolecular sequence alignment into a problem of searching for optimal or nearoptimal points in an 'alignment space', a genetic algorithm can be used to find good alignments very efficiently. Results: Experiments on real data sets have shown that the average computing time of this technique may be two or three orders lower than that of a technique based on pairwise dynamic programming, while the alignment qualities are very similar. Availability: A C program on UNIX has been written to implement the technique. It is available on request from the authors. Contact:
On the allocation of documents in multiprocessor information retrieval systems
 In Proceedings of the Fourteenth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
, 1991
"... Abstract. Information retrieval is the selection of documents that are potentially relevant to a user’s information need. Given the vast volume of data stored in modern information retrieval systems, searching the document database requires vast computational resources. To meet these computational d ..."
Abstract

Cited by 16 (0 self)
 Add to MetaCart
Abstract. Information retrieval is the selection of documents that are potentially relevant to a user’s information need. Given the vast volume of data stored in modern information retrieval systems, searching the document database requires vast computational resources. To meet these computational demands, various researchers have developed parallel information retrieval systems. As efficient exploitation of parallelism demands fast access to the documents, data organization and placement significantly affect the total processing time. We describe and evaluate a data placement strategy for distributed memory, distributed 1/0 multicomputers. Initially, a formal description of the Multiprocessor Document Allocation Problem (MDAP) and a proof that MDAP is NP Complete are presented. A document allocation
Spectral Landscape Theory
 Evolutionary Dynamics—Exploring the Interplay of Selection, Neutrality, Accident, and Function
, 1999
"... INTRODUCTION Evolutionary change is caused by the spontaneously generated genetic variation and its subsequent fixation by drift and/or selection. Consequently, the main focus of evolutionary theory has been to understand the genetic structure and dynamics of populations, see e.g. [101]. In recent ..."
Abstract

Cited by 8 (3 self)
 Add to MetaCart
INTRODUCTION Evolutionary change is caused by the spontaneously generated genetic variation and its subsequent fixation by drift and/or selection. Consequently, the main focus of evolutionary theory has been to understand the genetic structure and dynamics of populations, see e.g. [101]. In recent years, however, alternative approaches have gained increasing prominence in evolutionary theory. This development has been stimulated to some extent by the application of evolutionary models to designing evolutionary algorithms such as Genetic Al Evolutionary Dynamics edited by J.P. Crutchfield and P. Schuster, 1999 2 Spectral Landscape Theory gorithms, Evolution Strategies, and Genetic Programming, as well as by the theory of Complex Adaptive Systems [69, 79, 38]. The generic structure of an evolutionary model is x 0 = S (x; w) ffi T (x;<F