Recurrent neural networks can represent and process simple context-free languages. However, the diiculty of nding with gradient-based learning appropriate weights for context-free language prediction motivates an investigation on the applicability of evolutionary algorithms. By empirical studies , an evolutionary algorithm proves to be more reliable in nding prediction solutions to a simple CFL...

Several evolutionary algorithms have been proposed for robot path planning. Most existing methods fo r evolutionary path planning require a number of generations for finding a satisfactory trajectory and thus are not e@cient enough for real-time applications. In this paper we present a new method for evolutionary path planning whach can be used on-line in real-time. We use an evolutionary algor...

In this paper we study age-varying plasticities across different components in an artificial neural network performing a reinforcement learning task. An evolutionary algorithm is given the task of mapping the age of agents to the plasticity levels of different network components. The results show that patterns of plasticity resembling biological sensitive periods appear, and that these periods ...

development of any organization largely depends on the proper use of its human resources. as organizations become much larger, these problems are naturally added to these enormous labor force. one of the topics organizational communities of irancan be considered as a unfamiliar subject and less likely to be found in research is the phenomenon of organizational silence; despite the fact that sil...

We provide an algorithm to compute near-optimal strategies for the Cultaptation social learning game. We show that the strategies produced by our algorithm are near-optimal, both in their expected utility and their expected reproductive success. We show how our algorithm can be used to provide insight into evolutionary conditions under which learning is best done by copying others, versus the c...

The pace of progress in the fields of Evolutionary Computation and Machine Learning is currently limited — in the former field, by the improbability of making advantageous extensions to evolutionary algorithms when their capacity for adaptation is poorly understood, and in the latter by the difficulty of finding effective semi-principled reductions of hard realworld problems to relatively simpl...

Evolutionary algorithms commonly search for the best solutions by maintaining a population of individuals that evolves from one generation to the next. The evolution consists of selecting a set of individuals from the population and applying, to some subsets of it, recombination operators that create new solutions. In this paper, Estimation of distribution algorithms arise as an alternative to ...

Continuous action policy search, the search for efficient policies in continuous control tasks, is currently the focus of intensive research driven both by the recent success of deep reinforcement learning algorithms and by the emergence of competitors based on evolutionary algorithms. In this paper, we present a broad survey of policy search methods, incorporating into a common big picture the...

Learning Classifier Systems use evolutionary algorithms to facilitate rule-discovery, where rule fitness is traditionally payoff based and assigned under a sharing scheme. Most current research has shifted to the use of an accuracy-based scheme where fitness is based on a rule's ability to predict the expected payoff from its use. Learning Classifier Systems which build anticipations of the exp...

This paper addresses the issue of reducing the storage requirements on Instance-Based Learning algorithms. Algorithms proposed by other researches use heuristics to prune instances of the training set or modify the instances themselves to achieve a reduced set of instances. Our work presents an alternative way. We propose to induce a reduced set of partially-defined instances with Evolutionary ...