Learning and Evolution

By Stefano Nolfi, Dario Floreano. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “In EPANNs, similarly complex interaction dynamics between evolution and learning were also observed (Nolfi and Floreano, 1999).”
Evolving Childhood's Length and Learning Parameters in an Intrinsically Motivated Reinforcement Learning Robot (2007, unknown): “Recently (Schembri et al., 2007b) we have proposed an architecture, based on a hierarchical actorcritic reinforcement-learning model (Sutton and Barto, 1998), which overcomes both these limits of IMRL by integrating it with 'Evolutionary Robotics (ER)' framework (Nolfi and Floreano, 1999).”
Neuromodulation and plasticity in an autonomous robot (2002, background): “Robot learning is an active and rapidly progressing area of research ( Nolfi & Floreano, 1999; Schaal, 2002; Sharkey, 1997; Touretzky & Saksida, 1997).”
Evolving plastic neural networks with novelty search (2010, background): “Keywords Novelty search, neural networks, adaptation, learning, neuromodulation, neuroevolution”
How novelty search escapes the deceptive trap of learning to learn (2009, background): “There is much evidence that both processes are integral to the success of biological evolution [14, 16] and that lifetime learning can itself help to guide evolution to higher fitness [7], which is called the Baldwin Effect.”
A Bayesian approach to the evolution of social learning (2012, background): “A number of authors have criticized this approach to the evolution of social learning on the grounds that social learning and individual learning are not psychologically distinct processes (Heyes, 1994; Plotkin, 1988).”
Evolution and Learning in an Intrinsically Motivated Reinforcement Learning Robot (2007, background): “This approach already highlighted several important aspects of the relationship (for a review, see [3]), for example the fact that learning can guide evolutionary search [4] and that evolution can discover good starting conditions which can in turn facilitate learning processes during lifetime [5].”
Adaptation of Robot Behaviour through Online Evolution and Neuromodulated Learning (2012, background): “There is much evidence that: (i) both processes are integral to the success of evolution in both biological and artificial systems [14, 19], and (ii) that learning can accelerate the evolution of good solutions [9], which is known as the Baldwin effect.”
Neuroevolution: from architectures to learning (2008, unknown): “with some form of learning [55].”
Evolutionary robotics: coping with environmental change (2000, background): “This strategy not only can improve the search properties of artificial evolution, but can also make the controller more robust to changes that occur faster than the evolutionary time scale (i.e., changes that occur during the life of an individual) ( Nolfi & Floreano, 1999 ).”
The challenges of joint attention (2006, background): “However, such kinds of evolutionary approaches do not directly deal with the development of turn-taking behavior (but some researchers argue that these two forms of adaptive processes have complementary characteristics and can be effectively integrated (Nolfi and Parisi, 1997; Floreano and Mondada, ”
Incremental Evolution of Complex General Behavior (1997, background): “1 Introduction Neuro-Evolution(NE), the training of Arti cial Neural Networks with Genetic Algorithms, has proven an attractive alternative to standard learning methods in reinforcement environments (Colombetti and Dorigo 1992; Nol et al. 1990; Nol and Parisi 1995; Yamauchi and Beer 1994).”