Combining fitness-based search and user modeling in evolutionary robotics

Bongard, Josh; Hornby, Gregory S.

doi:10.1145/2463372.2500097

Cited by 21 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They demonstrated the technique in the deceptive maze navigation domain [186]. Interactive evolution has also been used to help mitigate premature convergence (see section 2.2.1, paragraph "semiinteractive evolution") [22,31].…”

Section: Reality Gapmentioning

confidence: 99%

“…Celis et al [31] investigated this idea in a system in which the user demonstrates what he or she prefers, in a quadruped robot locomotion and in an obstacle avoidance task. Using a similar task, Bongard and Hornby also introduced a multi-objective approach in which a surrogate user (which stands for the user) deflects the search away from local optima and a traditional fitness function leads the search toward the global optimum [22].…”

Section: Semi-interactive Evolutionmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Reality Gapmentioning

confidence: 99%

Section: Semi-interactive Evolutionmentioning

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

show abstract

“…Interactive models are proposed by IEA's, in which collaboration between a specific evolutionary algorithm and human prevents the search from getting stuck in local optima [14]. In general, Interactive Evolutionary Algorithms (IEA) [13] have been method of choice in many experiments such as Evolutionary Robotics [15] and Computer Graphics [16].…”

Section: Related Workmentioning

confidence: 99%

An apprenticeship learning hyper-heuristic for vehicle routing in HyFlex

Asta

Özcan

2014

2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS)

View full text Add to dashboard Cite

Abstract-Apprenticeship learning occurs via observations while an expert is in action. A hyper-heuristic is a search method or a learning mechanism that controls a set of low level heuristics or combines different heuristic components to generate heuristics for solving a given computationally hard problem. In this study, we investigate into a novel apprenticeshiplearning-based approach which is used to automatically generate a hyper-heuristic for vehicle routing. This approach itself can be considered as a hyper-heuristic which operates in a train and test fashion. A state-of-the-art hyper-heuristic is chosen as an expert which is the winner of a previous hyper-heuristic competition. Trained on small vehicle routing instances, the learning approach yields various classifiers, each capturing different actions that the expert hyper-heuristic performs during the search process. Those classifiers are then used to produce a hyper-heuristic which is potentially capable of generalizing the actions of the expert hyperheuristic while solving the unseen instances. The experimental results on vehicle routing using the Hyper-heuristic Flexible (HyFlex) framework shows that the apprenticeship-learningbased hyper-heuristic delivers an outstanding performance when compared to the expert and some other previously proposed hyper-heuristics.

show abstract

“…Yet the benefit of human intuition does not only apply to search spaces with hard to define or subjective optimization metrics. In fact, recent experiments suggest that humans are capable of interleaving their own intuition with automated algorithms, yielding better results than the automated algorithms can alone (Bongard and Hornby, 2013;Woolley and Stanley, 2014). In an ideal world, any experiment would have the ability to leverage human intelligence to aid the search while also allowing discovered results to remain accessible to the community in perpetuity for future extension by humans, or by some clever algorithm.…”

Section: Introductionmentioning

confidence: 99%

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

Szerlip

Stanley

2014

Artificial Life 14: Proceedings of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems

View full text Add to dashboard Cite

Natural evolution inspires the fields of evolutionary computation (EC) and artificial life (ALife). A prominent feature of natural evolution is that it effectively never ends. However, most EC and ALife experiments are only run for several days or weeks at a time. Once an experiment concludes, reproducing, observing, or extending the results often requires considerable effort. In contrast, some Collaborative Interactive Evolution (CIE) systems, e.g. Picbreeder, were designed to preserve results as potential stepping stones to build upon later while taking advantage of human insight to solve challenging problems. Traditionally, building long-running and open experiments similar to Picbreeder presents a complex and timeconsuming software challenge. To reduce this challenge and thereby remove the barrier to situating almost any experiment within an interactive online framework, this paper presents the initial prototype for Worldwide Infrastructure for Neuroevolution (WIN). Built in the model of Picbreeder, WIN is a modular library for significantly reducing the complexity of creating fully persistent, online, and interactive evolutionary platforms for any new or existing domain. WIN Online, the public interface for WIN, provides an online collection of domains built with WIN that lets novice and expert users browse and meaningfully contribute to ongoing experiments. Two example experiments in this paper demonstrate WIN's potential to quickly bootstrap any evolutionary domain with online and interactive capabilities.

show abstract

Combining fitness-based search and user modeling in evolutionary robotics

Cited by 21 publications

References 23 publications

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

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

An apprenticeship learning hyper-heuristic for vehicle routing in HyFlex

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

Contact Info

Product

Resources

About