{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:39:33Z","timestamp":1779295173140,"version":"3.51.4"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T00:00:00Z","timestamp":1665705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005416","name":"Norges Forskningsr\u00e5d","doi-asserted-by":"publisher","award":["270961"],"award-info":[{"award-number":["270961"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:p>In this work, we argue that the search for Artificial General Intelligence should start from a much lower level than human-level intelligence. The circumstances of intelligent behavior in nature resulted from an organism interacting with its surrounding environment, which could change over time and exert pressure on the organism to allow for learning of new behaviors or environment models. Our hypothesis is that learning occurs through interpreting sensory feedback when an agent acts in an environment. For that to happen, a body and a reactive environment are needed. We evaluate a method to evolve a biologically-inspired artificial neural network that learns from environment reactions named Neuroevolution of Artificial General Intelligence, a framework for low-level artificial general intelligence. This method allows the evolutionary complexification of a randomly-initialized spiking neural network with adaptive synapses, which controls agents instantiated in mutable environments. Such a configuration allows us to benchmark the adaptivity and generality of the controllers. The chosen tasks in the mutable environments are food foraging, emulation of logic gates, and cart-pole balancing. The three tasks are successfully solved with rather small network topologies and therefore it opens up the possibility of experimenting with more complex tasks and scenarios where curriculum learning is beneficial.<\/jats:p>","DOI":"10.3389\/frobt.2022.1007547","type":"journal-article","created":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T04:54:30Z","timestamp":1665723270000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Towards the Neuroevolution of Low-level artificial general intelligence"],"prefix":"10.3389","volume":"9","author":[{"given":"Sidney","family":"Pontes-Filho","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristoffer","family":"Olsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anis","family":"Yazidi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael A.","family":"Riegler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P\u00e5l","family":"Halvorsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Nichele","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,10,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1101\/lm.960510","article-title":"An elegant mind: Learning and memory in caenorhabditis elegans","volume":"17","author":"Ardiel","year":"2010","journal-title":"Learn. Mem."},{"key":"B2","first-page":"41","article-title":"Curriculum learning","author":"Bengio","year":"2009"},{"key":"B3","volume-title":"Anatomy and physiology","author":"Betts","year":"2013"},{"key":"B4","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1113\/jphysiol.1980.sp013097","article-title":"Visual pigments of rods and cones in a human retina","volume":"298","author":"Bowmaker","year":"1980","journal-title":"J. Physiology"},{"key":"B5","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"B6","doi-asserted-by":"publisher","first-page":"2745","DOI":"10.3390\/ma12172745","article-title":"Neuromorphic spiking neural networks and their memristor-cmos hardware implementations","volume":"12","author":"Camu\u00f1as-Mesa","year":"2019","journal-title":"Materials"},{"key":"B7","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1038\/s42256-019-0050-3","article-title":"The animal-ai olympics","volume":"1","author":"Crosby","year":"2019","journal-title":"Nat. Mach. Intell."},{"key":"B8","doi-asserted-by":"publisher","first-page":"99","DOI":"10.3389\/fncom.2015.00099","article-title":"Unsupervised learning of digit recognition using spike-timing-dependent plasticity","volume":"9","author":"Diehl","year":"2015","journal-title":"Front. Comput. Neurosci."},{"key":"B9","doi-asserted-by":"publisher","first-page":"4","DOI":"10.3389\/frobt.2015.00004","article-title":"Evolutionary robotics: What, why, and where to","volume":"2","author":"Doncieux","year":"2015","journal-title":"Front. Robot. AI"},{"key":"B10","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1162\/106454698568639","article-title":"Evolutionary body building: Adaptive physical designs for robots","volume":"4","author":"Funes","year":"1998","journal-title":"Artif. Life"},{"key":"B11","article-title":"Weight agnostic neural networks","volume-title":"Advances in Neural Information Processing Systems","author":"Gaier","year":"2019"},{"key":"B12","first-page":"195","article-title":"The influence of the sigmoid function parameters on the speed of backpropagation learning","author":"Han","year":"1995"},{"key":"B13","volume-title":"The organization of behavior: A neuropsychological theory","author":"Hebb","year":"1949"},{"key":"B14","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1038\/scientificamerican0792-66","article-title":"Genetic algorithms","volume":"267","author":"Holland","year":"1992","journal-title":"Sci. Am."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1569","DOI":"10.1109\/tnn.2003.820440","article-title":"Simple model of spiking neurons","volume":"14","author":"Izhikevich","year":"2003","journal-title":"IEEE Trans. Neural Netw."},{"key":"B16","doi-asserted-by":"publisher","first-page":"e45717","DOI":"10.7554\/elife.45717","article-title":"Dual separable feedback systems govern firing rate homeostasis","volume":"8","author":"Kulik","year":"2019","journal-title":"Elife"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e253","DOI":"10.1017\/s0140525x16001837","article-title":"Building machines that learn and think like people","volume":"40","author":"Lake","year":"2017","journal-title":"Behav. Brain Sci."},{"key":"B18","doi-asserted-by":"crossref","DOI":"10.4324\/9780429032769","volume-title":"Artificial life: Proceedings of an interdisciplinary workshop on the synthesis and simulation of living systems","author":"Langton","year":"2019"},{"key":"B19","doi-asserted-by":"publisher","first-page":"4906","DOI":"10.1038\/srep04906","article-title":"Activity-dependent synaptic plasticity of a chalcogenide electronic synapse for neuromorphic systems","volume":"4","author":"Li","year":"2014","journal-title":"Sci. Rep."},{"key":"B20","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1023\/a:1008916026143","article-title":"Spike-frequency adaptation of a generalized leaky integrate-and-fire model neuron","volume":"10","author":"Liu","year":"2001","journal-title":"J. Comput. Neurosci."},{"key":"B21","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1007\/bf02481333","article-title":"Evolving robot morphology and control","volume":"4","author":"Mautner","year":"2000","journal-title":"Artif. Life Robot."},{"key":"B22","doi-asserted-by":"publisher","first-page":"5257","DOI":"10.1109\/tnnls.2020.2965567","article-title":"A brain-inspired framework for evolutionary artificial general intelligence","volume":"31","author":"Nadji-Tehrani","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"B23","first-page":"20719","article-title":"Meta-Learning through Hebbian Plasticity in Random Networks","volume-title":"Advances in Neural Information Processing Systems","author":"Najarro","year":"2020"},{"key":"B24","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"B25","volume-title":"Neuroevolution of artificial general intelligence","author":"Olsen","year":"2020"},{"key":"B26","volume-title":"Handbook of the normal distribution","author":"Patel","year":"1996"},{"key":"B27","first-page":"1","article-title":"Bidirectional learning for robust neural networks","author":"Pontes-Filho","year":"2019"},{"key":"B28","article-title":"A conceptual bio-inspired framework for the evolution of artificial general intelligence","author":"Pontes-Filho","year":"2019"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.3389\/frobt.2022.1007547","article-title":"Towards the neuroevolution of low-level artificial general intelligence","author":"Pontes-Filho","year":"2022"},{"key":"B30","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.conb.2020.11.001","article-title":"Measuring and modeling whole-brain neural dynamics in caenorhabditis elegans","volume":"65","author":"Randi","year":"2020","journal-title":"Curr. Opin. Neurobiol."},{"key":"B31","article-title":"A generalist agent","author":"Reed","year":"2022"},{"key":"B32","first-page":"533","article-title":"Indirectly encoding neural plasticity as a pattern of local rules","author":"Risi","year":"2010"},{"key":"B33","unstructured":"The future of artificial intelligence is self-organizing and self-assembling RisiS. 2021"},{"key":"B34","article-title":"Towards out-of-distribution generalization: A survey","author":"Shen","year":"2021"},{"key":"B35","first-page":"2557","article-title":"Evolving adaptive neural networks with and without adaptive synapses","author":"Stanley","year":"2003"},{"key":"B36","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1038\/s42256-018-0006-z","article-title":"Designing neural networks through neuroevolution","volume":"1","author":"Stanley","year":"2019","journal-title":"Nat. Mach. Intell."},{"key":"B37","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1162\/106365602320169811","article-title":"Evolving neural networks through augmenting topologies","volume":"10","author":"Stanley","year":"2002","journal-title":"Evol. Comput."},{"key":"B38","doi-asserted-by":"publisher","first-page":"e2018459118","DOI":"10.1073\/pnas.2018459118","article-title":"Neuronal circuits overcome imbalance in excitation and inhibition by adjusting connection numbers","volume":"118","author":"Sukenik","year":"2021","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"B39","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neunet.2018.12.002","article-title":"Deep learning in spiking neural networks","volume":"111","author":"Tavanaei","year":"2019","journal-title":"Neural Netw."},{"key":"B40","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1162\/artl_a_00290","article-title":"Evolutionary innovations and where to find them: Routes to open-ended evolution in natural and artificial systems","volume":"25","author":"Taylor","year":"2019","journal-title":"Artif. Life"},{"key":"B41","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-1-4615-5529-2_1","article-title":"Learning to learn: Introduction and overview","volume-title":"Learning to learn","author":"Thrun","year":"1998"},{"key":"B42","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780199568413.001.0001","volume-title":"Fundamentals of computational neuroscience","author":"Trappenberg","year":"2009"},{"key":"B43","doi-asserted-by":"crossref","DOI":"10.1109\/CEC.1999.781944","article-title":"Embodied evolution: Embodying an evolutionary algorithm in a population of robots","author":"Watson","year":"1999"},{"key":"B44","unstructured":"Evolving networks WelleckS. 2019"},{"key":"B45","doi-asserted-by":"publisher","first-page":"3770","DOI":"10.1038\/s41467-019-11786-6","article-title":"A critique of pure learning and what artificial neural networks can learn from animal brains","volume":"10","author":"Zador","year":"2019","journal-title":"Nat. Commun."},{"key":"B46","doi-asserted-by":"crossref","DOI":"10.1109\/ISCAS51556.2021.9401262","article-title":"Metaplasticnet: Architecture with probabilistic metaplastic synapses for continual learning","author":"Zohora","year":"2021"}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2022.1007547\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T22:00:19Z","timestamp":1701208819000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2022.1007547\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,14]]},"references-count":46,"alternative-id":["10.3389\/frobt.2022.1007547"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2022.1007547","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,14]]},"article-number":"1007547"}}