检索结果-内蒙古大学图书馆

2nd Genetic and Evolutionary Computation Conference (GECCO)

作者： Cazenille, Leo Ochanomizu Univ Tokyo Japan

ISBN: (纸本)9781450383509

quality-diversity algorithms search for large collections of diverse and high-performing solutions, rather than just for a single solution like typical optimisation methods. They are specially adapted for multi-modal problems that can be solved in many different ways, such as complex reinforcement learning or robotics tasks. However, these approaches are highly dependent on the choice of feature descriptors (FDs) quantifying the similarity in behaviour of the solutions. While FDs usually needs to be hand-designed, recent studies have proposed ways to define them automatically by using feature extraction techniques, such as PCA or Auto-Encoders, to learn a representation of the problem from previously explored solutions. Here, we extend these approaches to more complex problems which cannot be efficiently explored by relying only on a single representation but require instead a set of diverse and complementary representations. We describe MC-AURORA, a quality-diversity approach that optimises simultaneously several collections of solutions, each with a different set of FDs, which are, in turn, defined automatically by an ensemble of modular auto-encoders. We show that this approach produces solutions that are more diverse than those produced by single-representation approaches.

关键词： quality-diversity algorithms AURORA Evolutionary Robotics Ensemble representation learning Auto-encoders Deep Learning

来源：评论

学校读者我要写书评

暂无评论

QED: Using quality-Environment-diversity to Evolve Resilient Robot Swarms

引用

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION 2021年第2期25卷 346-357页

作者： Bossens, David M. Tarapore, Danesh Univ Southampton Sch Elect & Comp Sci Southampton SO17 1BJ Hants England

In quality-diversity algorithms, the behavioral diversity metric is a key design choice that determines the quality of the evolved archives. Although behavioral diversity is traditionally obtained by describing the observed resulting behavior of robot controllers evaluated in a single environment, it is often more easily induced by introducing environmental diversity, i.e., by manipulating the environments in which the controllers are evaluated. This article proposes quality-environment-diversity (QED), an algorithm that repeatedly generates a random environment according to a probability distribution over environmental features (e.g., number of obstacles, arena size and robot sensor and actuator characteristics), evaluates the controller in that environment, and then describes the controller in terms of the features of that environment, the environment descriptor. Our study compares QED to three baseline task-specific and generic behavioral descriptors, in 5 different robot swarm benchmark tasks. For each task, the quality of the evolved archives is assessed by their capability to provide high-performing compensatory behaviors following injection of 250 unique faults to the robots of the swarm. The evolved archives achieve a median 2- to 3-fold reduction in the impact of the faults on the performance of the swarm. A qualitative analysis of evolved archives is done by visualizing the relation between diversity of compensatory behaviors, here called useful behavioral diversity, and fault recovery metrics. The resulting signatures indicate that, due to the diversity of environments inducing useful behavioral diversity, archives evolved by QED provide robot swarm controllers that are capable of recovering from high-impact faults.

关键词： Robot kinematics Robot sensing systems Task analysis Swarm robotics Legged locomotion Actuators Behavioral diversity evolutionary robotics fault recovery quality-diversity algorithms swarm robotics

来源：评论

学校读者我要写书评

暂无评论

Self-Referential quality diversity Through Differential Map-Elites

Self-Referential Quality Diversity Through Differential Map-...

引用

2nd Genetic and Evolutionary Computation Conference (GECCO)

作者： Choi, Tae Jong Togelius, Julian Kyungil Univ Gyongsan South Korea NYU Brooklyn NY 11201 USA

ISBN: (纸本)9781450383509

Differential MAP-Elites is a novel algorithm that combines the illumination capacity of CVT-MAP-Elites with the continuous-space optimization capacity of Differential Evolution. The algorithm is motivated by observations that illumination algorithms, and quality-diversity algorithms in general, offer qualitatively new capabilities and applications for evolutionary computation yet are in their original versions relatively unsophisticated optimizers. The basic Differential MAP-Elites algorithm, introduced for the first time here, is relatively simple in that it simply combines the operators from Differential Evolution with the map structure of CVT-MAP-Elites. Experiments based on 25 numerical optimization problems suggest that Differential MAP-Elites clearly outperforms CVT-MAP-Elites, finding better-quality and more diverse solutions.

关键词： Artificial intelligence Evolutionary algorithms quality-diversity algorithms Numerical optimization

来源：评论

学校读者我要写书评

暂无评论

Illuminating super mario bros: quality-diversity within platformer level generation 20

Illuminating super mario bros: Quality-diversity within plat...

引用

2020 Genetic and Evolutionary Computation Conference, GECCO 2020

作者： Withington, Oliver Queen Mary University of London United Kingdom

ISBN: (纸本)9781450371278

We aim to build on the current understanding of how quality-diversity (QD) algorithms can be applied to Procedural Content Generation (PCG) for video games with our platform, Illuminated-Mario. The work presented here has two core aims: to explore the viability of our approach to PCG and to compare the performances of MAP-Elites and SHINE, two state of the art QD algorithms. Our experimental results suggest both that our approach to level generation is a viable foundation for future PCG systems, and that while the SHINE variants implemented do not significantly outperform MAP-Elites, they warrant further investigation. © 2020 Owner/Author.

关键词： super mario PCG quality-diversity algorithms

来源：评论

学校读者我要写书评

暂无评论

Increasing Trust in Meta-Heuristics by Using MAP-Elites 19

Increasing Trust in Meta-Heuristics by Using MAP-Elites

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Urquhart, Neil Guckert, Michael Powers, Simon Edinburgh Napier Univ Sch Comp Edinburgh Midlothian Scotland TH Mittelhessen Giessen Germany

ISBN: (纸本)9781450367486

Intelligent AI systems using approaches containing emergent elements often encounter acceptance problems. Results do not get sufficiently explained and the procedure itself can not be fully retraced because the flow of control is dependent on stochastic elements. Trust in such algorithms must be established so that users will accept results, without questioning whether the algorithm is sound. In this position paper we present an approach in which the user gets involved in the optimization procedure by letting them chose alternative solutions from a structure-archive which is created by the MAP-Elites algorithm. Analysis of these alternatives along the criteria of multiobjective optimization problems makes solutions comprehensible and hence is a means to build trust. We propose that the solution-focused nature of MAP-Elites allows the history of a solution to be easily shown to the user, explaining why that solution was included in those presented to the user. Here we demonstrate our ideas using a logistics problem previously explored by the authors.

关键词： Vehicle Routing quality-diversity algorithms

来源：评论

学校读者我要写书评

暂无评论

Exploring Self-Assembling Behaviors in a Swarm of Bio-micro-robots using Surrogate-Assisted MAP-Elites

Exploring Self-Assembling Behaviors in a Swarm of Bio-micro-...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Cazenille, Leo Bredeche, Nicolas Aubert-Kato, Nathanael Ochanomizu Univ Dept Informat Sci Tokyo Japan Sorbonne Univ Inst Syst Intelligents & Robot ISIR CNRS F-75005 Paris France

ISBN: (纸本)9781728124858

Swarms of molecular robots are a promising approach to create specific shapes at the microscopic scale through self-assembly. However, controlling their behavior is a challenging problem as it involves complex non-linear dynamics and high experimental variability. Hand-crafting a molecular controller will often be time-consuming and give sub-optimal results. Optimization methods, like the BIONEAT algorithm, were previously employed to partially overcome these difficulties, but they still had to cope with deceptive high-dimensional search spaces and computationally expensive simulations. Here, we describe a novel approach to solve this problem by using MAP-Elites, an algorithm that searches for both high-performing and diverse solutions. We then apply it to a molecular robotic framework we recently introduced that allows sensing, signaling and self-assembly at the micro-scale and show that MAP-Elites outperforms previous approaches. Additionally, we propose a surrogate model of micro-robots physics and chemical reaction dynamics to reduce the computational costs of simulation. We show that the resulting methodology is capable of optimizing controllers with similar accuracy as when using only a full-fledged realistic model, with half the computational budget.

关键词： Bio-micro-robots swarm robotics molecular programming evolutionary robotics surrogate models quality-diversity algorithms MAP-Elites

来源：评论

学校读者我要写书评

暂无评论

Evolving Gaits for Damage Control in a Hexapod Robot

Evolving Gaits for Damage Control in a Hexapod Robot

引用

2nd Genetic and Evolutionary Computation Conference (GECCO)

作者： Mailer, Christopher Nitschke, Geoff Raw, Leanne Univ Cape Town Cape Town South Africa

ISBN: (纸本)9781450383509

Autonomous robots are increasingly used in remote and hazardous environments, where damage to sensory-actuator systems cannot be easily repaired. Such robots must therefore have controllers that continue to function effectively given unexpected malfunctions and damage to robot morphology. This study applies the Intelligent Trial and Error (IT&E) algorithm to adapt hexapod robot control to various leg failures and demonstrates the IT&E map-size parameter as a critical parameter in influencing IT&E adaptive task performance. We evaluate robot adaptation for multiple leg failures on two different map-sizes in simulation and validate evolved controllers on a physical hexapod robot. Results demonstrate a trade-off between adapted gait speed and adaptation duration, dependent on adaptation task complexity (leg damage incurred), where map-size is crucial for generating behavioural diversity required for adaptation.

关键词： Evolutionary Robotics quality-diversity algorithms Bayesian optimisation Damage recovery Behavioural diversity

来源：评论

学校读者我要写书评

暂无评论

Learning behaviour-performance maps with meta-evolution

Learning behaviour-performance maps with meta-evolution

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Bossens, David M. Mouret, Jean-Baptiste Tarapore, Danesh Univ Southampton Southampton Hants England Univ Lorraine INRIA CNRS Nancy France

ISBN: (纸本)9781450371285

The MAP-Elites quality-diversity algorithm has been successful in robotics because it can create a behaviorally diverse set of solutions that later can be used for adaptation, for instance to unanticipated damages. In MAP-Elites, the choice of the behaviour space is essential for adaptation, the recovery of performance in unseen environments, since it defines the diversity of the solutions. Current practice is to hand-code a set of behavioural features, however, given the large space of possible behaviour-performance maps, the designer does not know a priori which behavioural features maximise a map's adaptation potential. We introduce a new meta-evolution algorithm that discovers those behavioural features that maximise future adaptations. The proposed method applies Covariance Matrix Adaptation Evolution Strategy to evolve a population of behaviour-performance maps to maximise a meta-fitness function that rewards adaptation. The method stores solutions found by MAP-Elites in a database which allows to rapidly construct new behaviour-performance maps on-the-fly. To evaluate this system, we study the gait of the RHex robot as it adapts to a range of damages sustained on its legs. When compared to MAP-Elites with user-defined behaviour spaces, we demonstrate that the meta-evolution system learns high-performing gaits with or without damages injected to the robot.

关键词： quality-diversity algorithms behavioural diversity meta-learning evolutionary robotics damage recovery

来源：评论

学校读者我要写书评

暂无评论

An Illumination Algorithm Approach to Solving the Micro-Depot Routing Problem

An Illumination Algorithm Approach to Solving the Micro-Depo...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Urquhart, Neil Hoehl, Silke Hart, Emma Napier Univ Sch Comp Edinburgh Midlothian Scotland Frankfurt Univ Appl Sci Frankfurt Germany

ISBN: (纸本)9781450361118

An increasing emphasis on reducing pollution and congestion in city centres combined with an increase in online shopping is changing the ways in which logistics companies address vehicle routing problems (VRP). We introduce the micro-depot-VRP, in which a single supply vehicle is used to supply a set of micro-depots distributed across a city;deliveries are then made from the micro-depot by couriers using electric vehicles, bicycles and on foot. We present a formal definition of the problem, and propose a representation that can be used with an optimisation algorithm to minimise the total cost associated with delivering packages. Using five instances created from real-data obtained from delivery companies operating within the City of Frankfurt, we apply an illumination algorithm in order to obtain a set of results that minimise costs but have differing characteristics in terms of emissions, distance travelled and number of couriers used. Results show that solutions can be obtained that have equivalent costs to the baseline standard VRP solution, but considerably improve on this in terms of minimising the secondary criteria relating to emissions, couriers and distance.

关键词： Vehicle Routing quality-diversity algorithms

来源：评论

学校读者我要写书评

暂无评论

Minimize Surprise MAP-Elites: A Task-Independent MAP-Elites Variant for Swarms 22

Minimize Surprise MAP-Elites: A Task-Independent MAP-Elites ...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Kaiser, Tanja Katharina Hamann, Heiko Univ Lubeck Lubeck Germany

ISBN: (纸本)9781450392686

Swarm robotics controllers are often automatically generated using methods of evolutionary computation with a task-specific fitness function to guide the optimization process. By contrast, our minimize surprise approach uses a task-independent fitness function to generate diverse behaviors over several independent evolutionary runs. Alternatives are divergent search algorithms rewarding behavioral novelty, such as novelty search, and quality-diversity algorithms generating diverse high-quality solutions, such as MAP-Elites. These approaches usually rely on task-dependent measures. We propose Minimize Surprise MAP-Elites, a task-independent MAP-Elites variant that combines MAP-Elites with our minimize surprise approach. Our first experiments result in high-quality solutions that lead to behavioral diversity across tasks and within tasks.

关键词： quality-diversity algorithms behavioral diversity swarm robotics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：