Exploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs

By Jesper Blynel, Dario Floreano. 2003

81 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems 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 Control and Systems Engineering

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “That study put forward the idea that the learning of plastic networks as described in Blynel and Floreano (2002, 2003) was at that point still a proof-of-concept rather than a superior learning tool because networks with ﬁxed weights could achieve similar performance.”
Evolving Neural Turing Machines for Reward-based Learning (2016, background): “Adaptive neural networks can either change through local Hebbian learning rules [6], in which connection weights are modified based on neural activation [14, 4], or recurrent neural networks (RNNs) that store activation patterns through recurrent connections [1].”
Continual and One-Shot Learning Through Neural Networks with Dynamic External Memory (2017, background): “Adaptive neural networks can either change through local Hebbian learning rules [18], in which connection weights are modified based on neural activation [8, 9, 14], or recurrent neural networks (RNNs) that store activation patterns through recurrent connections [10].”
Neuroevolution: from architectures to learning (2008, background): “Floreano and Mattiussi [19] evolved networks of spiking neurons for solving a non-trivial vision-based navigation task.”
A unified approach to evolving plasticity and neural geometry (2012, background): “Blynel and Floreano [3] also solved a version of the continuous task, but with CTRNNs instead of plastic networks, which often required incremental evolution.”
Evolving plastic neural networks with novelty search (2010, methodology): “This domain is ideal to test the hypothesis that novelty search escapes deception in adaptive domains because it is well-established from prior work (Blynel & Floreano, 2003; Dürr, Mattiussi, Soltoggio, & Floreano, 2008; Soltoggio et al., 2007, 2008) and can be adjusted to be more or less…”
Indirectly Encoding Neural Plasticity as a Pattern of Local Rules (2010, background): “T-Mazes are often studied in the context of operant conditioning of animals; they are also studied to assess the ability of plastic ANNs [3, 14].”
Continual Learning through Evolvable Neural Turing Machines (2016, background): “In order to enable these evolving ANNs to learn during their lifetime, efforts have been made to allow them to adapt online and learn from past experience [10, 11, 12, 13, 14].”
In search of intelligence: evolving a developmental neuron capable of learning (2014, background): “A maze represents a complex and confusing series of pathways usually considered as an important task environment for autonomous robot navigation and route optimisation (Blynel & Floreano, 2003; Tani, 1996).”
Novelty of behaviour as a basis for the neuro-evolution of operant reward learning (2009, background): “Inaninitial phase, two versions of a T-maze environment [3] are used to evolve either conservative or novel behaviours.”
Evolutionary and Computational Advantages of Neuromodulated Plasticity (2008, methodology): “10) were employed in robotic navigation tasks in (Floreano and Urzelai, 2001b,a; Urzelai and Floreano, 2001; Nolfi and Floreano, 2002; Blynel and Floreano, 2003).”
How novelty search escapes the deceptive trap of learning to learn (2009, methodology): “[16] S. Nolfi and D. Floreano.”
Evolving Spiking Networks with Variable Resistive Memories (2014, methodology): “…analysis), compared to “stateless” network models such as the multi layer perceptron (Rumelhart and McClelland, 1986; although 80 Evolutionary Computation Volume 22, Number 1 continuous time recurrent neural networks can use internal dynamics to the same effect, e.g., Blynel and Floreano, 2003).”