Creating High-Level Components with a Generative Representation for Body-Brain Evolution

By Gregory S. Hornby, Jordan B. Pollack. 2002

287 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): “…(Wagner and Altenberg, 1996; Pigliucci, 2008; Lehman and Stanley, 2013), the encoding of genetic information through the genotype-phenotype mapping processes (Hornby et al., 2002), and novelty search and the deception of ﬁtness objectives (Lehman and Stanley, 2008; Stanley and Lehman, 2015).”
Evolutionary Computation for Reinforcement Learning (2012, methodology): “For example, L-systems (Lindenmayer, 1968), which are formal grammars for describing complex recursive structures, have been used to evolve both the morphology and control system for autonomous robots, greatly outperforming direct encodings (Hornby and Pollack, 2002).”
A Taxonomy for Artificial Embryogeny (2003, methodology): “As the problems tackled with evolutionary computation become increasingly complex, it is becoming apparent that a direct mapping from genotype to phenotype, wherein each unit of the phenotype is represented by a single gene in the genotype, will no longer be effective [5, 9, 39].”
Quality Diversity: A New Frontier for Evolutionary Computation (2016, background): “Such aliasing, which is amplified especially in the presence of indirect genotype to phenotype mappings (Hornby and Pollack, 2001, 2002; Bongard, 2002; Stanley and Miikkulainen, 2003; Stanley, 2007), is thus counterproductive to find various behaviors, as shown empirically by Trujillo et al.”
Real-time neuroevolution in the NERO video game (2005, background): “Gruau et al. 1996; Hornby and Pollack 2002; Krishnan and Ciesielski 1994; Lee and Kim 1996; Mandischer”
Autonomous Evolution of Topographic Regularities in Artificial Neural Networks (2010, background): “In response to the limitations of direct encodings, other researchers have evolved indirectly encoded ANNs (Beer, 2000; Bentley and Kumar, 1999; Bongard, 2002; Dellaert and Beer, 1994; Gruau et al., 1996; Hornby, 2004; Hornby and Pollack, 2002; Husbands et al., 1998; Komosinski and Rotaru-Varga, 200”
Picbreeder: evolving pictures collaboratively online (2008, background): “Particularly in evolutionary computation, significant research in recent years has sought to clarify how complex structures can be encoded most efficiently for evolutionary search [7, 18, 31, 32].”
A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks (2009, background): “Researchers in generative and developmental encoding , which is a branch of evolutionary computation concerned with genetic encodings motivated by biology, often point out that repetition through ge-netic reuse explains how such massive structures can be represented compactly in DNA [5, 23, 26, 52].”
Ieee Transactions on Evolutionary Computation on the Performance of Indirect Encoding across the Continuum of Regularity (unknown): “In at least two cases, an indirect encoding evolved both the gaits and the morphologies of creatures [11], [37].”
On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks (2013, background): “Inﬂuenced by this concept, many researchers proposed artiﬁcial developmental systems with diverse inspirations including chemical gradients [11,12], gene regulatory networks [13,14], cell divisions [15], computational neuro-science models [16] and L-systems [9].”
A novel generative encoding for exploiting neural network sensor and output geometry (2007, background): “A promising research area in indirect encoding is generative and developmental encoding, which is motivated from biology [1, 2, 8].”
Compositional Pattern Producing Networks : A Novel Abstraction of Development (2007, background): “This observation has inspired an active field of research in artificial developmental encodings [4, 10, 35, 74].”
AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence (2019, background): “Such specialization is especially easy to imagine if the bodies of virtual robots are simultaneously optimized, which is a subﬁeld with a long history [158, 21, 22, 67, 6, 57].”
Computer-automated Evolution of an X-band Antenna for Nasa's Space Technology 5 Mission (methodology): “The generative representation for encoding branching antennas is an extension of our previous work in using a linear-representation for encoding rodbased robots (Hornby et al., 2001, 2003; Hornby and Pollack, 2002).”
Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design Space (2011, background): “Particularly in evolutionary computation, significant research in recent years has sought to clarify how complex structures can be encoded most efficiently for evolutionary search (Bentley and Kumar, 1999; Hornby and Pollack, 2002; Stanley and Miikkulainen, 2004a, 2003; Angeline, 1995; Hart et al., ”
Single-unit pattern generators for quadruped locomotion (2013, background): “The simultaneous discovery of regularities is one reason indirect encodings [2, 5, 13, 16, 22, 32] have become an important area of research.”
Compositional pattern producing networks: A novel abstraction of development (2007, background): “Both approaches have produced significant results, including simulated threedimensional body morphologies and locomotion [7, 15], neural networks with repeating structures [21, 27], and physical structures with self-similarity [7, 17].”