This letter uses a modified form of the NK model introduced to explore aspects of distributed control. In particular, a previous result suggesting the use of dynamically formed subgroups within the overall system can be more effective than global control is further explored. The conditions under which the beneficial distributed control emerges are more clearly identified, and the reason for the benefit over traditional global control is suggested as a generally applicable dropout mechanism to improve learning in such systems.
{"title":"A Generalised Dropout Mechanism for Distributed Systems","authors":"Larry Bull;Haixia Liu","doi":"10.1162/artl_a_00393","DOIUrl":"10.1162/artl_a_00393","url":null,"abstract":"This letter uses a modified form of the NK model introduced to explore aspects of distributed control. In particular, a previous result suggesting the use of dynamically formed subgroups within the overall system can be more effective than global control is further explored. The conditions under which the beneficial distributed control emerges are more clearly identified, and the reason for the benefit over traditional global control is suggested as a generally applicable dropout mechanism to improve learning in such systems.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":"29 2","pages":"146-152"},"PeriodicalIF":2.6,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9677771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cooperation among individuals has been key to sustaining societies. However, natural selection favors defection over cooperation. Cooperation can be favored when the mobility of individuals allows cooperators to form a cluster (or group). Mobility patterns of animals sometimes follow a Lévy flight. A Lévy flight is a kind of random walk but it is composed of many small movements with a few big movements. The role of Lévy flights for cooperation has been studied by Antonioni and Tomassini, who showed that Lévy flights promoted cooperation combined with conditional movements triggered by neighboring defectors. However, the optimal condition for neighboring defectors and how the condition changes with the intensity of Lévy flights are still unclear. Here, we developed an agent-based model in a square lattice where agents perform Lévy flights depending on the fraction of neighboring defectors. We systematically studied the relationships among three factors for cooperation: sensitivity to defectors, the intensity of Lévy flights, and population density. Results of evolutionary simulations showed that moderate sensitivity most promoted cooperation. Then, we found that the shortest movements were best for cooperation when the sensitivity to defectors was high. In contrast, when the sensitivity was low, longer movements were best for cooperation. Thus, Lévy flights, the balance between short and long jumps, promoted cooperation in any sensitivity, which was confirmed by evolutionary simulations. Finally, as the population density became larger, higher sensitivity was more beneficial for cooperation to evolve. Our study highlights that Lévy flights are an optimal searching strategy not only for foraging but also for constructing cooperative relationships with others.
{"title":"How Lévy Flights Triggered by the Presence of Defectors Affect Evolution of Cooperation in Spatial Games","authors":"Genki Ichinose;Daiki Miyagawa;Erika Chiba;Hiroki Sayama","doi":"10.1162/artl_a_00382","DOIUrl":"10.1162/artl_a_00382","url":null,"abstract":"Cooperation among individuals has been key to sustaining societies. However, natural selection favors defection over cooperation. Cooperation can be favored when the mobility of individuals allows cooperators to form a cluster (or group). Mobility patterns of animals sometimes follow a Lévy flight. A Lévy flight is a kind of random walk but it is composed of many small movements with a few big movements. The role of Lévy flights for cooperation has been studied by Antonioni and Tomassini, who showed that Lévy flights promoted cooperation combined with conditional movements triggered by neighboring defectors. However, the optimal condition for neighboring defectors and how the condition changes with the intensity of Lévy flights are still unclear. Here, we developed an agent-based model in a square lattice where agents perform Lévy flights depending on the fraction of neighboring defectors. We systematically studied the relationships among three factors for cooperation: sensitivity to defectors, the intensity of Lévy flights, and population density. Results of evolutionary simulations showed that moderate sensitivity most promoted cooperation. Then, we found that the shortest movements were best for cooperation when the sensitivity to defectors was high. In contrast, when the sensitivity was low, longer movements were best for cooperation. Thus, Lévy flights, the balance between short and long jumps, promoted cooperation in any sensitivity, which was confirmed by evolutionary simulations. Finally, as the population density became larger, higher sensitivity was more beneficial for cooperation to evolve. Our study highlights that Lévy flights are an optimal searching strategy not only for foraging but also for constructing cooperative relationships with others.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":"29 2","pages":"187-197"},"PeriodicalIF":2.6,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10047984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The ability to express diverse behaviors is a key requirement for most biological systems. Underpinning behavioral diversity in the natural world is the embodied interaction between the brain, body, and environment. Dynamical systems form the basis of embodied agents, and can express complex behavioral modalities without any conventional computation. While significant study has focused on designing dynamical systems agents with complex behaviors, for example, passive walking, there is still a limited understanding about how to drive diversity in the behavior of such systems. In this article, we present a novel hardware platform for studying the emergence of individual and collective behavioral diversity in a dynamical system. The platform is based on the so-called Bernoulli ball, an elegant fluid dynamics phenomenon in which spherical objects self-stabilize and hover in an airflow. We demonstrate how behavioral diversity can be induced in the case of a single hovering ball via modulation of the environment. We then show how more diverse behaviors are triggered by having multiple hovering balls in the same airflow. We discuss this in the context of embodied intelligence and open-ended evolution, suggesting that the system exhibits a rudimentary form of evolutionary dynamics in which balls compete for favorable regions of the environment and exhibit intrinsic “alive” and “dead” states based on their positions in or outside of the airflow.
{"title":"On the Stability and Behavioral Diversity of Single and Collective Bernoulli Balls","authors":"Toby Howison;Harriet Crisp;Simon Hauser;Fumiya Iida","doi":"10.1162/artl_a_00395","DOIUrl":"10.1162/artl_a_00395","url":null,"abstract":"The ability to express diverse behaviors is a key requirement for most biological systems. Underpinning behavioral diversity in the natural world is the embodied interaction between the brain, body, and environment. Dynamical systems form the basis of embodied agents, and can express complex behavioral modalities without any conventional computation. While significant study has focused on designing dynamical systems agents with complex behaviors, for example, passive walking, there is still a limited understanding about how to drive diversity in the behavior of such systems. In this article, we present a novel hardware platform for studying the emergence of individual and collective behavioral diversity in a dynamical system. The platform is based on the so-called Bernoulli ball, an elegant fluid dynamics phenomenon in which spherical objects self-stabilize and hover in an airflow. We demonstrate how behavioral diversity can be induced in the case of a single hovering ball via modulation of the environment. We then show how more diverse behaviors are triggered by having multiple hovering balls in the same airflow. We discuss this in the context of embodied intelligence and open-ended evolution, suggesting that the system exhibits a rudimentary form of evolutionary dynamics in which balls compete for favorable regions of the environment and exhibit intrinsic “alive” and “dead” states based on their positions in or outside of the airflow.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":"29 2","pages":"168-186"},"PeriodicalIF":2.6,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9728828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
generative artificial intelligence (AI) tools like large-language models (
{"title":"Editorial: What Have Large-Language Models and Generative Al Got to Do With Artificial Life?","authors":"Alan Dorin;Susan Stepney","doi":"10.1162/artl_e_00409","DOIUrl":"10.1162/artl_e_00409","url":null,"abstract":"generative artificial intelligence (AI) tools like large-language models (","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":"29 2","pages":"141-145"},"PeriodicalIF":2.6,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9674009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Most models of migration simply assume that migrants somehow make their way from their point of origin to their chosen destination. We know, however, that—especially in the case of asylum migration—the migrant journey often is a hazardous, difficult process where migrants make decisions based on limited information and under severe material constraints. Here we investigate the dynamics of the migration journey itself using a spatially explicit, agent-based model. In particular we are interested in the effects of limited information and information exchange. We find that under limited information, migration routes generally become suboptimal, their stochasticity increases, and migrants arrive much less frequently at their preferred destination. Under specific circumstances, self-organised consensus routes emerge that are largely unpredictable. Limited information also strongly reduces the migrants’ ability to react to changes in circumstances. We conclude, first, that information and information exchange is likely to have considerable effects on all aspects of migration and should thus be included in future modelling efforts and, second, that there are many questions in theoretical migration research that are likely to profit from the use of agent-based modelling techniques.
{"title":"The Effects of Information on the Formation of Migration Routes and the Dynamics of Migration","authors":"Martin Hinsch;Jakub Bijak","doi":"10.1162/artl_a_00388","DOIUrl":"10.1162/artl_a_00388","url":null,"abstract":"Most models of migration simply assume that migrants somehow make their way from their point of origin to their chosen destination. We know, however, that—especially in the case of asylum migration—the migrant journey often is a hazardous, difficult process where migrants make decisions based on limited information and under severe material constraints. Here we investigate the dynamics of the migration journey itself using a spatially explicit, agent-based model. In particular we are interested in the effects of limited information and information exchange. We find that under limited information, migration routes generally become suboptimal, their stochasticity increases, and migrants arrive much less frequently at their preferred destination. Under specific circumstances, self-organised consensus routes emerge that are largely unpredictable. Limited information also strongly reduces the migrants’ ability to react to changes in circumstances. We conclude, first, that information and information exchange is likely to have considerable effects on all aspects of migration and should thus be included in future modelling efforts and, second, that there are many questions in theoretical migration research that are likely to profit from the use of agent-based modelling techniques.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":"29 1","pages":"3-20"},"PeriodicalIF":2.6,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9285347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hian Lee Kwa;Victor Babineau;Julien Philippot;Roland Bouffanais
There has been growing interest in the use of multi-robot systems in various tasks and scenarios. The main attractiveness of such systems is their flexibility, robustness, and scalability. An often overlooked yet promising feature is system modularity, which offers the possibility of harnessing agent specialization, while also enabling system-level upgrades. However, altering the agents’ capacities can change the exploration–exploitation balance required to maximize the system’s performance. Here, we study the effect of a swarm’s heterogeneity on its exploration–exploitation balance while tracking multiple fast-moving evasive targets under the cooperative multi-robot observation of multiple moving targets framework. To this end, we use a decentralized search and tracking strategy with adjustable levels of exploration and exploitation. By indirectly tuning the balance, we first confirm the presence of an optimal balance between these two key competing actions. Next, by substituting slower moving agents with faster ones, we show that the system exhibits a performance improvement without any modifications to the original strategy. In addition, owing to the additional amount of exploitation carried out by the faster agents, we demonstrate that a heterogeneous system’s performance can be further improved by reducing an agent’s level of connectivity, to favor the conduct of exploratory actions. Furthermore, in studying the influence of the density of swarming agents, we show that the addition of faster agents can counterbalance a reduction in the overall number of agents while maintaining the level of tracking performance. Finally, we explore the challenges of using differentiated strategies to take advantage of the heterogeneous nature of the swarm.
{"title":"Adapting the Exploration–Exploitation Balance in Heterogeneous Swarms: Tracking Evasive Targets","authors":"Hian Lee Kwa;Victor Babineau;Julien Philippot;Roland Bouffanais","doi":"10.1162/artl_a_00390","DOIUrl":"10.1162/artl_a_00390","url":null,"abstract":"There has been growing interest in the use of multi-robot systems in various tasks and scenarios. The main attractiveness of such systems is their flexibility, robustness, and scalability. An often overlooked yet promising feature is system modularity, which offers the possibility of harnessing agent specialization, while also enabling system-level upgrades. However, altering the agents’ capacities can change the exploration–exploitation balance required to maximize the system’s performance. Here, we study the effect of a swarm’s heterogeneity on its exploration–exploitation balance while tracking multiple fast-moving evasive targets under the cooperative multi-robot observation of multiple moving targets framework. To this end, we use a decentralized search and tracking strategy with adjustable levels of exploration and exploitation. By indirectly tuning the balance, we first confirm the presence of an optimal balance between these two key competing actions. Next, by substituting slower moving agents with faster ones, we show that the system exhibits a performance improvement without any modifications to the original strategy. In addition, owing to the additional amount of exploitation carried out by the faster agents, we demonstrate that a heterogeneous system’s performance can be further improved by reducing an agent’s level of connectivity, to favor the conduct of exploratory actions. Furthermore, in studying the influence of the density of swarming agents, we show that the addition of faster agents can counterbalance a reduction in the overall number of agents while maintaining the level of tracking performance. Finally, we explore the challenges of using differentiated strategies to take advantage of the heterogeneous nature of the swarm.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":"29 1","pages":"21-36"},"PeriodicalIF":2.6,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10639859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Since the beginning of the COVID-19 pandemic, various models of virus spread have been proposed. While most of these models focused on the replication of the interaction processes through which the virus is passed on from infected agents to susceptible ones, less effort has been devoted to the process through which agents modify their behaviour as they adapt to the risks posed by the pandemic. Understanding the way agents respond to COVID-19 spread is important, as this behavioural response affects the dynamics of virus spread by modifying interaction patterns. In this article, we present an agent-based model that includes a behavioural module determining agent testing and isolation propensity in order to understand the role of various behavioural parameters in the spread of COVID-19.
{"title":"Self-Isolation and Testing Behaviour During the COVID-19 Pandemic: An Agent-Based Model","authors":"Umberto Gostoli;Eric Silverman","doi":"10.1162/artl_a_00392","DOIUrl":"10.1162/artl_a_00392","url":null,"abstract":"Since the beginning of the COVID-19 pandemic, various models of virus spread have been proposed. While most of these models focused on the replication of the interaction processes through which the virus is passed on from infected agents to susceptible ones, less effort has been devoted to the process through which agents modify their behaviour as they adapt to the risks posed by the pandemic. Understanding the way agents respond to COVID-19 spread is important, as this behavioural response affects the dynamics of virus spread by modifying interaction patterns. In this article, we present an agent-based model that includes a behavioural module determining agent testing and isolation propensity in order to understand the role of various behavioural parameters in the spread of COVID-19.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":"29 1","pages":"94-117"},"PeriodicalIF":2.6,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10734655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In many social, cyber-physical, and socio-technical systems, a group of autonomous peers can encounter a knowledge aggregation problem, requiring them to organise themselves, without a centralised authority, as a distributed information processing unit (DIP). In this article, we specify and implement a new algorithm for knowledge aggregation based on Nowak’s psychological theory Regulatory Theory of Social Influence (RTSI). This theory posits that social influence consists of not only sources trying to influence targets, but also targets seeking sources by whom to be influenced and learning what processing rules those sources are using. A multi-agent simulator SMARTSIS is implemented to evaluate the algorithm, using as its base scenario a linear public goods game where the DIP’s decision is a qualitative question of distributive justice. In a series of experiments examining the emergence of expertise, we show how RTSI enhances the effectiveness of the multi-agent DIP as a social group while conserving each agent’s individual resources. Additionally, we identify eight criteria for evaluating the DIP unit’s performance, consisting of four conflicting pairs of systemic drivers, and discuss how RTSI maintains a balanced tension between the four driver pairs through the emergence and divergence of expertise. We conclude by arguing that this shows how psychological theories like RTSI can have a crucial role in informing agent-based models of human behaviour, which in turn may be critically important for effective knowledge management and reflective self-improvement in both cyber-physical and socio-technical systems.
{"title":"Expertise, Social Influence, and Knowledge Aggregation in Distributed Information Processing","authors":"Asimina Mertzani;Jeremy Pitt;Andrzej Nowak;Tomasz Michalak","doi":"10.1162/artl_a_00387","DOIUrl":"10.1162/artl_a_00387","url":null,"abstract":"In many social, cyber-physical, and socio-technical systems, a group of autonomous peers can encounter a knowledge aggregation problem, requiring them to organise themselves, without a centralised authority, as a distributed information processing unit (DIP). In this article, we specify and implement a new algorithm for knowledge aggregation based on Nowak’s psychological theory Regulatory Theory of Social Influence (RTSI). This theory posits that social influence consists of not only sources trying to influence targets, but also targets seeking sources by whom to be influenced and learning what processing rules those sources are using. A multi-agent simulator SMARTSIS is implemented to evaluate the algorithm, using as its base scenario a linear public goods game where the DIP’s decision is a qualitative question of distributive justice. In a series of experiments examining the emergence of expertise, we show how RTSI enhances the effectiveness of the multi-agent DIP as a social group while conserving each agent’s individual resources. Additionally, we identify eight criteria for evaluating the DIP unit’s performance, consisting of four conflicting pairs of systemic drivers, and discuss how RTSI maintains a balanced tension between the four driver pairs through the emergence and divergence of expertise. We conclude by arguing that this shows how psychological theories like RTSI can have a crucial role in informing agent-based models of human behaviour, which in turn may be critically important for effective knowledge management and reflective self-improvement in both cyber-physical and socio-technical systems.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":"29 1","pages":"37-65"},"PeriodicalIF":2.6,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9284835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Social search has stably evolved across various species and is often used by humans to search for resources (such as food, information, social partners). In turn, these resources frequently come distributed in patches or clusters. In the current work, we use an ecologically inspired agent-based model to investigate whether social search and clustering are stable outcomes of the dynamical mutual interactions between the two. While previous research has studied unidirectional influences of social search on resource clustering and vice versa, the current work investigates the consequential patterns emerging from their two-way interactions over time. In our model, consumers evolved search strategies (ranging from competitive to social) as adaptations to their environmental resource structures, and resources varied in distributions (ranging from random to clustered) that were shaped by agents’ consumption patterns. Across four experiments, we systematically analyzed the patterns of influence that search strategies and environment structure have on each other to identify stable attractor states of both. In Experiment 1, we fixed resource clustering at various levels and observed its influence on social search, and in Experiment 2, we observed the influence of social search on resource distribution. In both these experiments we found that increasing levels of one variable produced increases in the other; however, at very high levels of the manipulated variable, the dependent variable tended to fall. Finally in Experiments 3 and 4, we studied the dynamics that arose when resource clustering and social search could both change and mutually influence each other, finding that low levels of social search and clustering were stable attractor states. Our simple 2D model yielded results that qualitatively resemble those across a wide range of search domains (from physical search for food to abstract search for information), highlighting some stable outcomes of mutually interacting consumer/resource systems.
{"title":"Social Search and Resource Clustering as Emergent Stable States","authors":"Mahi Luthra;Peter M. Todd","doi":"10.1162/artl_a_00391","DOIUrl":"10.1162/artl_a_00391","url":null,"abstract":"Social search has stably evolved across various species and is often used by humans to search for resources (such as food, information, social partners). In turn, these resources frequently come distributed in patches or clusters. In the current work, we use an ecologically inspired agent-based model to investigate whether social search and clustering are stable outcomes of the dynamical mutual interactions between the two. While previous research has studied unidirectional influences of social search on resource clustering and vice versa, the current work investigates the consequential patterns emerging from their two-way interactions over time. In our model, consumers evolved search strategies (ranging from competitive to social) as adaptations to their environmental resource structures, and resources varied in distributions (ranging from random to clustered) that were shaped by agents’ consumption patterns. Across four experiments, we systematically analyzed the patterns of influence that search strategies and environment structure have on each other to identify stable attractor states of both. In Experiment 1, we fixed resource clustering at various levels and observed its influence on social search, and in Experiment 2, we observed the influence of social search on resource distribution. In both these experiments we found that increasing levels of one variable produced increases in the other; however, at very high levels of the manipulated variable, the dependent variable tended to fall. Finally in Experiments 3 and 4, we studied the dynamics that arose when resource clustering and social search could both change and mutually influence each other, finding that low levels of social search and clustering were stable attractor states. Our simple 2D model yielded results that qualitatively resemble those across a wide range of search domains (from physical search for food to abstract search for information), highlighting some stable outcomes of mutually interacting consumer/resource systems.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":"29 1","pages":"118-140"},"PeriodicalIF":2.6,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9300250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kevin Godin-Dubois;Sylvain Cussat-Blanc;Yves Duthen
While interest in artificial neural networks (ANNs) has been renewed by the ubiquitous use of deep learning to solve high-dimensional problems, we are still far from general artificial intelligence. In this article, we address the problem of emergent cognitive capabilities and, more crucially, of their detection, by relying on co-evolving creatures with mutable morphology and neural structure. The former is implemented via both static and mobile structures whose shapes are controlled by cubic splines. The latter uses ESHyperNEAT to discover not only appropriate combinations of connections and weights but also to extrapolate hidden neuron distribution. The creatures integrate low-level perceptions (touch/pain proprioceptors, retina-based vision, frequency-based hearing) to inform their actions. By discovering a functional mapping between individual neurons and specific stimuli, we extract a high-level module-based abstraction of a creature’s brain. This drastically simplifies the discovery of relationships between naturally occurring events and their neural implementation. Applying this methodology to creatures resulting from solitary and tag-team co-evolution showed remarkable dynamics such as range-finding and structured communication. Such discovery was made possible by the abstraction provided by the modular ANN which allowed groups of neurons to be viewed as functionally enclosed entities.
{"title":"Explaining the Neuroevolution of Fighting Creatures Through Virtual fMRI","authors":"Kevin Godin-Dubois;Sylvain Cussat-Blanc;Yves Duthen","doi":"10.1162/artl_a_00389","DOIUrl":"10.1162/artl_a_00389","url":null,"abstract":"While interest in artificial neural networks (ANNs) has been renewed by the ubiquitous use of deep learning to solve high-dimensional problems, we are still far from general artificial intelligence. In this article, we address the problem of emergent cognitive capabilities and, more crucially, of their detection, by relying on co-evolving creatures with mutable morphology and neural structure. The former is implemented via both static and mobile structures whose shapes are controlled by cubic splines. The latter uses ESHyperNEAT to discover not only appropriate combinations of connections and weights but also to extrapolate hidden neuron distribution. The creatures integrate low-level perceptions (touch/pain proprioceptors, retina-based vision, frequency-based hearing) to inform their actions. By discovering a functional mapping between individual neurons and specific stimuli, we extract a high-level module-based abstraction of a creature’s brain. This drastically simplifies the discovery of relationships between naturally occurring events and their neural implementation. Applying this methodology to creatures resulting from solitary and tag-team co-evolution showed remarkable dynamics such as range-finding and structured communication. Such discovery was made possible by the abstraction provided by the modular ANN which allowed groups of neurons to be viewed as functionally enclosed entities.","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":"29 1","pages":"66-93"},"PeriodicalIF":2.6,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9284827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：