Stefano Nolfi

Learn More
The paper describes simulations on populations of neural networks that both evolve at the population level and learn at the individual level. Unlike other simulations, the evolutionary task (finding food in the environment) and the learning task (predicting the next position of food on the basis of present position and planned network's movement) are(More)
This paper describes how agents can learn an internal model of the world structurally by focusing on the problem of behavior-based articulation. We develop an on-line learning scheme { the so-called mixture of recurrent neural net (RNN) experts { in which a set of RNN modules becomes self-organized as experts on multiple levels in order to account for the(More)
The problem of the validity of simulation is particularly relevant for methodologies that use machine learning techniques to develop control systems for autonomous robots, as, for instance, the artificial life approach known as evolutionary robotics. In fact, although it has been demonstrated that training or evolving robots in real environments is(More)
Coevolution (i.e., the evolution of two or more competing populations with coupled fitness) has several features that may potentially enhance the power of adaptation of artificial evolution. In particular, as discussed by Dawkins and Krebs [3], competing populations may reciprocally drive one another to increasing levels of complexity by producing an(More)
A new way of building control systems, known as behavior based robotics, has recently been proposed to overcome the difficulties of the traditional AI approach to robotics. This new approach is based upon the idea of providing the robot with a range of simple behaviors and letting the environment determine which behavior should have control at any given(More)
Much research has been dedicated recently to applying genetic algorithms to populations of neural networks. However, while in real organisms the inherited genotype maps in complex ways into the resulting phenotype, in most of this research the development process that creates the individual phenotype is ignored. In this paper we present a model of neural(More)
In the last few years several researchers have resorted to artificial evolution (e.g. genetic algorithms) and learning techniques (e.g. neural networks) for studying the interaction between learning and evolution. These studies have been conducted for two different purposes: (a) looking at the performance advantages obtained by combining these two adaptive(More)
Recently, a new approach involving a form of simulated evolution has been proposed to build autonomous robots. However, it is still not clear if this approach is adequate for real life problems. In this paper we show how control systems that perform a non-trivial sequence of behaviors can be obtained with this methodology by "canalizing" the evolutionary(More)