Novelty-Based Multiobjectivization

By Jean-Baptiste Mouret. 2011

175 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Computer Vision and Pattern Recognition

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 Computational Theory and Mathematics

In Computer Vision and Pattern Recognition

Citations in the corpus

Weight Agnostic Neural Networks (2019, background): “By formulating the search as a multi-objective optimization problem [52, 77] we take into account the size of the network as well as its performance when ranking it in the population.”
Abandoning Objectives: Evolution Through the Search for Novelty Alone (2011, methodology): “Recently, the results from the maze domain were replicated in Mouret (2009) and combined with a multi-objective EA that did not include a genetic diversity-maintenance technique as in NEAT and was initialized with random network topologies instead of minimal networks as in NEAT.”
On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks (2013, methodology): “This encoding has been previously employed in many papers, with similar parameters [4,50,66–68].”
Evolving a diversity of virtual creatures through novelty search and local competition (2011, background): “Such multiobjective search suggests a simple way to combine the drive to optimize performance with the search for novelty: Reward both performance and novelty at the same time by making them separate objectives in a multi-objective search [16].”
Revising the evolutionary computation abstraction: minimal criteria novelty search (2010, methodology): “Novelty search was introduced in Lehman and Stanley [16] and applied to a deceptive maze task; these results were replicated in Mouret [23] in combination with a multi-objective evolutionary algorithm .”
Quality Diversity: A New Frontier for Evolutionary Computation (2016, background): “…it to solving problems that were previously considered to be too difficult (Lehman and Stanley, 2008, 2010, 2011a,b; Kistemaker and Whiteson, 2011; Mouret, 2011; Risi et al., 2011; Mouret and Doncieux, 2012; Cully and Mouret, 2013; Gomes and Christensen, 2013; Gomes et al., 2013; Liapis et al.,…”
Evolvability Search: Directly Selecting for Evolvability in order to Study and Produce It (2016, background): “The maze navigation domain is an appropriate domain for testing Evolvability Search because it is complex enough to be interesting, but is also easy to visualize and understand [17, 23].”
Adaptation of Robot Behaviour through Online Evolution and Neuromodulated Learning (2012, unknown): “In this domain, open-ended evolutionary techniques such as novelty search have shown promising results [13, 16] and may complement our method.”
Evolving plastic neural networks with novelty search (2010, background): “…in a deceptive navigation domain that requires an agent to navigate through a maze to reach a specific goal location (Lehman & Stanley, 2008; Mouret, 2009), in evolving biped locomotion (Lehman & Stanley, 2010a), and in evolving a program for an artificial ant benchmark task (Lehman &…”