Steps Toward a Modular Library for Turning Any Evolutionary Domain into an Online Interactive Platform

Szerlip, Paul A.; Stanley, Kenneth O.

doi:10.7551/978-0-262-32621-6-ch147

Cited by 3 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 1994, Karl Sims demonstrated that artificial evolution can produce novel morphology that resembles organisms observed in nature [59,60]. Subsequent works further investigated morphology evolution [4,8,9,11,37,44,64,65,70], modular robotics [39,45,48,75], and evolving soft robots [17,20], using indirect encoding [5,6,7,23,61].…”

Section: Related Workmentioning

confidence: 99%

“…In 1994, Karl Sims demonstrated that artificial evolution can produce novel morphologies that resemble organisms observed in nature [51,52]. Subsequent works further investigated morphology evolution [5,31,38,56,57,62], modular robotics [33,39,42,67], and evolving soft robots [11,14] using indirect encoding [17,53]. Theo Jansen [27] used evolutionary computation to design physical Strandbeests that can walk on their own consuming only wind energy.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning for Improving Agent Design

Ha¹

2019

Artificial Life

View full text Add to dashboard Cite

In many reinforcement learning tasks, the goal is to learn a policy to manipulate an agent, whose design is fixed, to maximize some notion of cumulative reward. The design of the agent's physical structure is rarely optimized for the task at hand. In this work, we explore the possibility of learning a version of the agent's design that is better suited for its task, jointly with the policy. We propose an alteration to the popular OpenAI Gym framework, where we parameterize parts of an environment, and allow an agent to jointly learn to modify these environment parameters along with its policy. We demonstrate that an agent can learn a better structure of its body that is not only better suited for the task, but also facilitates policy learning. Joint learning of policy and structure may even uncover design principles that are useful for assisted-design applications.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Reinforcement Learning for Improving Agent Design

Ha¹

2019

Artificial Life

View full text Add to dashboard Cite

show abstract

“…Paul Szerlip and Ken Stanley are currently developing the Worldwide Infrastructure for Neuroevolution (WIN) project, which aims to provide a general-purpose solution that will greatly reduce the effort required to build such systems [124]. Also under development is an associated public web-based front end for ongoing experiments built with the WIN platform, called WIN Online.…”

Section: Worldwide Infrastructure For Neuroevolutionmentioning

confidence: 99%

“…It can be run from any browser without installation-embedded visualization is implemented using Googleʼs Chart API, 124 and the server side is implemented using a variety of modern technologies based on Java virtual machines ( JVMs). Without the need for installation, the authors argue that COEL has a larger potential audience than existing desktop-based systems.…”

Section: Coelmentioning

confidence: 99%

WebAL Comes of Age: A Review of the First 21 Years of Artificial Life on the Web

et al. 2016

View full text Add to dashboard Cite

We present a survey of the first 21 years of web-based artificial life (WebAL) research and applications, broadly construed to include the many different ways in which artificial life and web technologies might intersect. Our survey covers the period from 1994-when the first WebAL work appeared-up to the present day, together with a brief discussion of relevant precursors. We examine recent projects, from 2010-2015, in greater detail in order to highlight the current state of the art. We follow the survey with a discussion of common themes and methodologies that can be observed in recent work and identify a number of likely directions for future work in this exciting area.

show abstract

“…http://winark.org/, a proposed framework for turning any evolutionary domain into an online interactive platform[29]. The modules are compiled with the Component 3…”

mentioning

confidence: 99%

Interactively Evolving Compositional Sound Synthesis Networks

Jónsson

Hoover

Risi

2015

Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

While the success of electronic music often relies on the uniqueness and quality of selected timbres, many musicians struggle with complicated and expensive equipment and techniques to create their desired sounds. Instead, this paper presents a technique for producing novel timbres that are evolved by the musician through interactive evolutionary computation. Each timbre is produced by an oscillator, which is represented by a special type of artificial neural network (ANN) called a compositional pattern producing network (CPPN). While traditional ANNs compute only sigmoid functions at their hidden nodes, CPPNs can theoretically compute any function and can build on those present in traditional synthesizers (e.g. square, sawtooth, triangle, and sine waves functions) to produce completely novel timbres. Evolved with NeuroEvolution of Augmenting Topologies (NEAT), the aim of this paper is to explore the space of potential sounds that can be generated through such compositional sound synthesis networks (CSSNs). To study the effect of evolution on subjective appreciation, participants in a listener study ranked evolved timbres by personal preference, resulting in preferences skewed toward the first and last generations. In the long run, the CSSN's ability to generate a variety of different and rich timbre opens up the intriguing possibility of evolving a complete CSSN-encoded synthesizer.

show abstract

Steps Toward a Modular Library for Turning Any Evolutionary Domain into an Online Interactive Platform

Cited by 3 publications

References 23 publications

Reinforcement Learning for Improving Agent Design

Reinforcement Learning for Improving Agent Design

WebAL Comes of Age: A Review of the First 21 Years of Artificial Life on the Web

Interactively Evolving Compositional Sound Synthesis Networks

Contact Info

Product

Resources

About