Evolving the Behavior of Machines: From Micro to Macroevolution

Mouret, Jean-Baptiste

doi:10.1016/j.isci.2020.101731

Cited by 11 publications

(11 citation statements)

References 101 publications

(160 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study highlights the deficiency of using a single fixed selection pressure based on task performance -by completely ignoring the objective it's possible to explore deceptive domains associated with the task fitness. However most behaviours are useless for the researchers goals, so to focus efforts, 'Quality Diversity' combines selection for both novelty and objective, resulting in only the fittest representatives for a diversity on behaviours creating competition within niches to breed the fittest solutions from all possible strategies [47][48][49] . Novelty search bares some similarity to natural complexification, with 'novelty' representing newly available niches, giving some support to the importance of gradual complexification in the discovery of complex behaviours.…”

Section: Conventional Evolutionary Computing Lacks This Open-ended Quality Usually Halting Asmentioning

confidence: 99%

How Biological Concepts and Evolutionary Theories Are Inspiring Advances in Machine Intelligence

Gutai¹,

Gorochowski²

2021

Preprint

View full text Add to dashboard Cite

Since its advent in the mid-twentieth century, the field of artificial intelligence (AI) has been heavily influenced by biology. From the structure of the brain to evolution by natural selection, core biological concepts underpin many of the fundamental breakthroughs in modern AI. Here, focusing specifically on artificial neural networks (ANNs) that have become commonplace in machine learning, we show the numerous connections between theories based on coevolution, multi-level selection, modularity and competition and related developments in ANNs. Our aim is to illuminate the valuable but often overlooked inspiration biologists have provided AI research and to spark future contributions at this intersection of biology and computer science. Although recent advances in AI have been swift, many significant challenges remain requiring innovative solutions. Thankfully, biology in all its forms still has a lot to teach us, especially when trying to create truly intelligent machines.

show abstract

Section: Conventional Evolutionary Computing Lacks This Open-ended Quality Usually Halting Asmentioning

confidence: 99%

How Biological Concepts and Evolutionary Theories Are Inspiring Advances in Machine Intelligence

Gutai¹,

Gorochowski²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…As such, QD algorithms are often called ‘illumination’ algorithms as they reveal entire areas of the feature-space of a problem. These algorithms were previously used to efficiently explore the space of a variety of problems in the robotics [ 30 , 31 ], reinforcement learning [ 32 – 34 ] and video games [ 35 , 36 ] communities, but they were also used to explore problems in biology and chemistry [ 25 , 37 , 38 ].…”

Section: Domain-level Explorationmentioning

confidence: 99%

Automated exploration of DNA-based structure self-assembly networks

2021

View full text Add to dashboard Cite

Finding DNA sequences capable of folding into specific nanostructures is a hard problem, as it involves very large search spaces and complex nonlinear dynamics. Typical methods to solve it aim to reduce the search space by minimizing unwanted interactions through restrictions on the design (e.g. staples in DNA origami or voxel-based designs in DNA Bricks). Here, we present a novel methodology that aims to reduce this search space by identifying the relevant properties of a given assembly system to the emergence of various families of structures (e.g. simple structures, polymers, branched structures). For a given set of DNA strands, our approach automatically finds chemical reaction networks (CRNs) that generate sets of structures exhibiting ranges of specific user-specified properties, such as length and type of structures or their frequency of occurrence. For each set, we enumerate the possible DNA structures that can be generated through domain-level interactions, identify the most prevalent structures, find the best-performing sequence sets to the emergence of target structures, and assess CRNs' robustness to the removal of reaction pathways. Our results suggest a connection between the characteristics of DNA strands and the distribution of generated structure families.

show abstract

“…One potential reason for the efficacy of QD algorithms is the notion that QD algorithms are better at promoting and exploiting stepping stones ( Mouret and Clune, 2015 ). In the context of EAs, we can describe a stepping stone, in its most basic form, as an intermediate step to a final solution ( Mouret, 2020 ). In that way, a stepping stone does not need to have any other quality apart from being in the genealogical ancestry of the concluding solution.…”

Section: Introductionmentioning

confidence: 99%

MAP-Elites Enables Powerful Stepping Stones and Diversity for Modular Robotics

et al. 2021

View full text Add to dashboard Cite

In modular robotics modules can be reconfigured to change the morphology of the robot, making it able to adapt to specific tasks. However, optimizing both the body and control of such robots is a difficult challenge due to the intricate relationship between fine-tuning control and morphological changes that can invalidate such optimizations. These challenges can trap many optimization algorithms in local optima, halting progress towards better solutions. To solve this challenge we compare three different Evolutionary Algorithms on their capacity to optimize high performing and diverse morphologies and controllers in modular robotics. We compare two objective-based search algorithms, with and without a diversity promoting objective, with a Quality Diversity algorithm—MAP-Elites. The results show that MAP-Elites is capable of evolving the highest performing solutions in addition to generating the largest morphological diversity. Further, MAP-Elites is superior at regaining performance when transferring the population to new and more difficult environments. By analyzing genealogical ancestry we show that MAP-Elites produces more diverse and higher performing stepping stones than the two other objective-based search algorithms. The experiments transitioning the populations to new environments show the utility of morphological diversity, while the analysis of stepping stones show a strong correlation between diversity of ancestry and maximum performance on the locomotion task. Together, these results demonstrate the suitability of MAP-elites for the challenging task of morphology-control search for modular robots, and shed light on the algorithm’s capability of generating stepping stones for reaching high-performing solutions.

show abstract

Evolving the Behavior of Machines: From Micro to Macroevolution

Cited by 11 publications

References 101 publications

How Biological Concepts and Evolutionary Theories Are Inspiring Advances in Machine Intelligence

How Biological Concepts and Evolutionary Theories Are Inspiring Advances in Machine Intelligence

Automated exploration of DNA-based structure self-assembly networks

MAP-Elites Enables Powerful Stepping Stones and Diversity for Modular Robotics

Contact Info

Product

Resources

About