Evolution of Plastic Control Networks

By Dario Floreano, J. Urzelai. 2001

76 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Mechanical Engineering

How researchers see this paper

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

In Artificial Intelligence

In Mechanical Engineering

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “…simulated and real robots with no speciﬁc assumptions on neural systems or plasticity (Smith, 2002), experiments suggested that neural control structures evolved with ﬁxed weights perform less well than plastic networks in robotic applications (Nolﬁ and Parisi, 1996; Floreano and Urzelai, 2001a).”
Neuroevolutionary reinforcement learning for generalized control of simulated helicopters (2011, background): “…in evolutionary robotics [20, 21, 45, 52, 64, 100], and some research has investigated customizing such methods to on-line settings [14, 15, 21, 65, 83, 89, 90], the problems tackled by evolutionary methods typically assume the availability of a ﬁtness function that requires only…”
Evolution of Reinforcement Learning in Uncertain Environments: A Simple Explanation for Complex Foraging Behaviors (2002, background): “In several recent papers, Floreano and Urzelai (e.g., Floreano & Urzelai, 2000, 2001) compared genetically determined synapses to adaptive synapses, in a sequential " light switching " problem.”
Neural Plasticity and Minimal Topologies for Reward-Based Learning (2008, unknown): “Unfortunately, the emergent properties of learning and memory make it difﬁcult to hand-design neural architectures for adaptive and learning robots and agents, and consequently evolutionary techniques are commonly used [6, 1, 5].”
Autonomous Evolution of Topographic Regularities in Artificial Neural Networks (2010, background): “…(including the visual cortex) exhibit synaptic plasticity (Hubel, Wiesel, & LeVay, 1977), ANNs with plastic synapses have been evolved in the past (Floreano & Urzelai 2000, 2001; Floreano & Mondada, 1996; Risi et al., 2009; Soltoggio et al., 2008), and in principle, HyperNEAT can potentially…”
Novelty of behaviour as a basis for the neuro-evolution of operant reward learning (2009, background): “Which approach leads to better evolution of adaptive behaviour is still debated [7, 15].”
Crossing the reality gap in evolutionary robotics by promoting transferable controllers (2010, background): “In [7], synaptic plasticity of neural network controllers is used to learn several sub-behaviors and also to overcome the gap when a solution is transferred onto the real device by adapting online to the “new” environment.”
Evolutionary Computation for Reinforcement Learning (2012, methodology): “…have also succeeded on-line (Steels, 1994; Nordin and Banzhaf, 1997; Schroder et al, 2001), especially in evolutionary robotics (Meyer et al, 1998; Floreano and Urzelai, 2001; Floreano and Mondada, 2002; Pratihar, 2003; Kernbach et al, 2009; Zufferey et al, 2010), and some research has…”
Neuroevolution: from architectures to learning (2008, background): “Floreano and Urzelai [ 22 ] also showed that a morphogenetic approach can greatly benefit from co-evolution of synaptic plasticity because the strengths of the growing connections are developed by learning rules that are coevolved with the developmental rules.”
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, ”
Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity (2009, unknown): “A similar but simple version of this task has, for example, been studied in [38].”
The Evolution of Learning Under Environmental Variability (2014, background): “Many experiments (see for instance Floreano and Urzelai (2001);”
The Transferability Approach: Crossing the Reality Gap in Evolutionary Robotics (2013, unknown): “In [17], plastic neural network controllers have been used to integrate several sub-behaviors and also to overcome a gap when a solution is transferred onto the real device by online adaptation to the “new” environment.”