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

Hornby, Gregory S.; Pollack, Jordan

doi:10.1162/106454602320991837

Cited by 181 publications

(157 citation statements)

References 20 publications

Supporting

Mentioning

155

Contrasting

Unclassified

Order By: Relevance

“…Evolutionary algorithms can be used in two different ways: to evolve a completely new system, or evolve a system that approximates some target system. Examples of the former approach involve the evolution of robot morphology/controller pairs [25] [19] [4] [10] and the use of genetic programming to evolve agent behaviors (eg. [17]).…”

Section: Introductionmentioning

confidence: 99%

Automating Genetic Network Inference with Minimal Physical Experimentation Using Coevolution

Bongard

Lipson

2004

Genetic and Evolutionary Computation – GECCO 2004

View full text Add to dashboard Cite

Abstract.A major challenge in system biology is the automatic inference of gene regulation network topology-an instance of reverse engineering-based on limited local data whose collection is costly and slow. Reverse engineering implies the reconstruction of a hidden system based only on input and output data sets generated by the target system. Here we present a generalized evolutionary algorithm that can reverse engineer a hidden network based solely on input supplied to the network and the output obtained, using a minimal number of tests of the physical system. The algorithm has two stages: the first stage evolves a system hypothesis, and the second stage evolves a new experiment that should be carried out on the target system in order to extract the most information. We present the general algorithm, which we call the estimation-exploration algorithm, and demonstrate it both for the inference of gene regulatory networks without the need to perform expensive and disruptive knockout studies, and the inference of morphological properties of a robot without extensive physical testing.

show abstract

Section: Introductionmentioning

confidence: 99%

Automating Genetic Network Inference with Minimal Physical Experimentation Using Coevolution

Bongard

Lipson

2004

Genetic and Evolutionary Computation – GECCO 2004

View full text Add to dashboard Cite

show abstract

“…The method for using generative representations to encode neural networks is the same as our earlier work [15], which we now summarize. First the generative representation (Sect.…”

Section: Evolution Of Parameter-controlled N-parity Networkmentioning

confidence: 99%

Generative Representations for Evolving Families of Designs

Hornby

2003

Genetic and Evolutionary Computation — GECCO 2003

Self Cite

View full text Add to dashboard Cite

Abstract. Since typical evolutionary design systems encode only a single artifact with each individual, each time the objective changes a new set of individuals must be evolved. When this objective varies in a way that can be parameterized, a more general method is to use a representation in which a single individual encodes an entire class of artifacts. In addition to saving time by preventing the need for multiple evolutionary runs, the evolution of parameter-controlled designs can create families of artifacts with the same style and a reuse of parts between members of the family. In this paper an evolutionary design system is described which uses a generative representation to encode families of designs. Because a generative representation is an algorithmic encoding of a design, its input parameters are a way to control aspects of the design it generates. By evaluating individuals multiple times with different input parameters the evolutionary design system creates individuals in which the input parameter controls specific aspects of a design. This system is demonstrated on two design substrates: neural-networks which solve the 3/5/7-parity problem and three-dimensional tables of varying heights.

show abstract

“…However, it has a side effect: it incentivizes researchers to work on what is not user-defined -the encoding and the evolutionary operators. As a result, evolutionary robotics focused for a long time on how to encode the morphology and the brain of robots (e.g., [165,114,85]) or how to encode neural networks (e.g., [95,123,171,50,59,128,169,35]). …”

Section: Introductionmentioning

confidence: 99%

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Doncieux

Mouret

2014

Evol. Intel.

View full text Add to dashboard Cite

Evolutionary robotics is often viewed as the application of a family of black-box optimization algorithms -evolutionary algorithms -to the design of robots, or parts of robots. When considering evolutionary robotics as black-box optimization, the selective pressure is mainly driven by a user-defined, black-box fitness function, and a domain-independent selection procedure. However, most evolutionary robotics experiments face similar challenges in similar setups: the selective pressure, and, in particular, the fitness function, is not a pure user-defined black box. The present review shows that, because evolutionary robotics experiments share common features, selective pressures for evolutionary robotics are a subject of research on their own. The literature has been split into two categories: goal refiners, aimed at changing the definition of a good solution, and process helpers, designed to help the search process. Two subcategories are further considered: task-specific approaches, which require knowledge on how to solve the task and taskagnostic ones, which do not need it. Besides highlighting the diversity of the approaches and their respective goals, the present review shows that many task-agnostic process helpers have been proposed during the last years, thus bringing us closer to the goal of a fully automated robot behavior design process.

show abstract

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

Cited by 181 publications

References 20 publications

Automating Genetic Network Inference with Minimal Physical Experimentation Using Coevolution

Automating Genetic Network Inference with Minimal Physical Experimentation Using Coevolution

Generative Representations for Evolving Families of Designs

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Contact Info

Product

Resources

About