Understanding Environmental Influence in an Open-Ended Evolutionary Algorithm

Abstract

Abstract. It is well known that in open-ended evolution, the nature of the environment plays in key role in directing evolution. However, in Evolutionary Robotics, it is often unclear exactly how parameterisation of a given environment might influence the emergence of particular behaviours. We consider environments in which the total amount of energy is parameterised by availability and value, and use surface plots to explore the relationship between those environment parameters and emergent behaviour using a variant of a well-known distributed evolutionary algorithm (mEDEA). Analysis of the resulting landscape show that it is crucial for a researcher to select appropriate parameterisations in order that the environment provides the right balance between facilitating survival and exerting sufficient pressure for new behaviours to emerge. To the best of our knowledge, this is the first time such an analysis has been undertaken.

The emergence of collective knowledge and cumulative culture in animals, humans and machines

“…Social learning algorithms, and more generally any learning algorithms distributed over a population of individuals whose learning both acts and depends on the social networks, are subject to two possibly antagonistic selective pressures. A given behaviour will diffuse in the population only (i) if it performs well with respect to the user-defined evaluation function, and (ii) if it is able to create opportunities for diffusion by meeting with other robots, which may also require learning basic survival skills not necessarily needed to fulfil the task given by the user [143][144][145][146]. The diffusion of behavioural strategies can be studied without any reference to the pursuit of a predefined goal; that is, in the absence of any user-defined objective function to be optimized.…”

Embodied Evolution in Collective Robotics: A Review

“…Haasdijk et al ( 2014a ) showed that these selection pressures can to some extent be modulated by tuning the ease with which robots can transmit genomes. Steyven et al ( 2016 ) showed that adjusting the availability and value of energy resources results in the evolution of a range of different behaviors. These results emphasize that tailoring the environmental requirements to transmit genomes can profoundly impact the evolutionary dynamics and that understanding these effects is vital to effectively develop embodied evolution systems.…”

“…Consequently, evolution experiences selection pressure from the aggregate of objective function(s) and environmental particularities. Steyven et al ( 2016 ) researched how aspects of the robots’ environment influence the emergence of particular behaviors and the balance between pressure toward survival and task. The objective may even pose requirements that are opposed to those by the environment.…”

An investigation of environmental influence on the benefits of adaptation mechanisms in evolutionary swarm robotics

“…is is particularly important for an open-ended distributed algorithm such as mEDEA in which survival of robots is crucial for evolution to occur. To counter this, Steyven et al [17] recently proposed a technique by which preliminary experimentation could be used to generate a surface-plot, highlighting regions of the parameter space in which the environment provides the right balance between facilitating survival and exerting su cient pressure for new behaviours to emerge. is enables a researcher to select appropriate se ings for experimentation.…”

“…Not for redistribution. e de nitive Version of Record was published in Proceedings of GECCO '17, July [15][16][17][18][19]2017 Adaptation o en takes one or all of three forms: evolutionary, individual and social learning. In evolutionary adaptation, information encoded on the genome adapts through selection and reproductive operators over many generations.…”