{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T04:21:58Z","timestamp":1777522918222,"version":"3.51.4"},"reference-count":41,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2020,6,7]],"date-time":"2020-06-07T00:00:00Z","timestamp":1591488000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"publisher","award":["Predictive Robots, grant agreement n.838861"],"award-info":[{"award-number":["Predictive Robots, grant agreement n.838861"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["Robotics for Microfarms (ROMI), grant agreement n."],"award-info":[{"award-number":["Robotics for Microfarms (ROMI), grant agreement n."]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Adaptive Behavior"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:p>This work presents an architecture that generates curiosity-driven goal-directed exploration behaviours for an image sensor of a microfarming robot. A combination of deep neural networks for offline unsupervised learning of low-dimensional features from images and of online learning of shallow neural networks representing the inverse and forward kinematics of the system have been used. The artificial curiosity system assigns interest values to a set of pre-defined goals and drives the exploration towards those that are expected to maximise the learning progress. We propose the integration of an episodic memory in intrinsic motivation systems to face catastrophic forgetting issues, typically experienced when performing online updates of artificial neural networks. Our results show that adopting an episodic memory system not only prevents the computational models from quickly forgetting knowledge that has been previously acquired but also provides new avenues for modulating the balance between plasticity and stability of the models.<\/jats:p>","DOI":"10.1177\/1059712320922916","type":"journal-article","created":{"date-parts":[[2020,6,8]],"date-time":"2020-06-08T01:05:15Z","timestamp":1591578315000},"page":"549-566","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":24,"title":["Intrinsic motivation and episodic memories for robot exploration of high-dimensional sensory spaces"],"prefix":"10.1177","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0975-1068","authenticated-orcid":false,"given":"Guido","family":"Schillaci","sequence":"first","affiliation":[{"name":"The BioRobotics Institute, Scuola Superiore Sant\u2019Anna, Pisa, Italy"},{"name":"Department of Excellence in Robotics & AI, Scuola Superiore Sant\u2019Anna, Pisa, Italy"}]},{"given":"Antonio","family":"Pico Villalpando","sequence":"additional","affiliation":[{"name":"Adaptive Systems Group, Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany"}]},{"given":"Verena V","family":"Hafner","sequence":"additional","affiliation":[{"name":"Adaptive Systems Group, Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany"}]},{"given":"Peter","family":"Hanappe","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories, Paris, France"}]},{"given":"David","family":"Colliaux","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories, Paris, France"}]},{"given":"Timoth\u00e9e","family":"Wintz","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories, Paris, France"}]}],"member":"179","published-online":{"date-parts":[[2020,6,7]]},"reference":[{"key":"bibr1-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1"},{"key":"bibr2-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1162\/isal_a_00031"},{"key":"bibr3-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.008"},{"key":"bibr4-1059712320922916","doi-asserted-by":"crossref","unstructured":"Botvinick M., Ritter S., Wang J. X., Kurth-Nelson Z., Blundell C., Hassabis D. (2019). Reinforcement learning, fast and slow. Trends in Cognitive Sciences. Advance online publication. https:\/\/doi.org\/10.1016\/j.tics.2019.02.006","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"bibr5-1059712320922916","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9320.001.0001"},{"key":"bibr6-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1111\/cdep.12282"},{"key":"bibr7-1059712320922916","doi-asserted-by":"crossref","unstructured":"Chen C. C., Chu H. T. (2005). Similarity measurement between images. In 29th annual international computer software and applications conference (Vol. 2., pp. 41\u201342). Institute of Electrical and Electronics Engineers. https:\/\/ieeexplore.ieee.org\/document\/1508081","DOI":"10.1109\/COMPSAC.2005.140"},{"key":"bibr8-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911410755"},{"key":"bibr9-1059712320922916","unstructured":"Colas C., Oudeyer P. Y., Sigaud O., Fournier P., Chetouani M. (2019). Curious: Intrinsically motivated modular multi-goal reinforcement learning. In International conference on machine learning (pp. 1331\u20131340). https:\/\/arxiv.org\/abs\/1810.06284"},{"key":"bibr10-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00016.2016"},{"key":"bibr11-1059712320922916","unstructured":"Forestier S., Mollard Y., Oudeyer P. Y. (2017). Intrinsically motivated goal exploration processes with automatic curriculum learning. Arxivpreprint Arxiv. https:\/\/arxiv.org\/abs\/1708.02190"},{"key":"bibr12-1059712320922916","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2013.00025"},{"key":"bibr13-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2787"},{"key":"bibr14-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2011.10.018"},{"key":"bibr15-1059712320922916","doi-asserted-by":"crossref","unstructured":"Isele D., Cosgun A. (2018). Selective experience replay for lifelong learning. In Thirty-second AAAI conference on artificial intelligence. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/viewFile\/16054\/16703","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"bibr16-1059712320922916","unstructured":"Kamra N., Gupta U., Liu Y. (2018). Deep generative dual memory network for continual learning. https:\/\/openreview.net\/forum?id=BkVsWbbAW"},{"key":"bibr17-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1016\/S0959-4388(99)00028-8"},{"key":"bibr18-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1177\/1059712318780679"},{"key":"bibr19-1059712320922916","doi-asserted-by":"crossref","unstructured":"Lin Z., Zhao T., Yang G., Zhang L. (2018). Episodic memory deep Q-networks. Arxivpreprint Arxiv. https:\/\/arxiv.org\/abs\/1805.07603","DOI":"10.24963\/ijcai.2018\/337"},{"key":"bibr20-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_7"},{"key":"bibr21-1059712320922916","doi-asserted-by":"crossref","unstructured":"Masse N. Y., Grant G. D., Freedman D. J. (2018). Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization. https:\/\/arxiv.org\/abs\/1802.01569","DOI":"10.1073\/pnas.1803839115"},{"key":"bibr22-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.102.3.419"},{"key":"bibr23-1059712320922916","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00504"},{"key":"bibr24-1059712320922916","volume-title":"International Symposium on Advanced Technologies and Management for Innovative Greenhouses","author":"Miranda L.","year":"2019"},{"key":"bibr25-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1016\/bs.pbr.2016.05.005"},{"key":"bibr26-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"bibr27-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"bibr28-1059712320922916","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2018.00078"},{"key":"bibr29-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"bibr30-1059712320922916","volume-title":"Humanoids 2012 Workshop on Developmental Robotics: Can Developmental Robotics Yield Human-Like Cognitive Abilities?","author":"Rolf M.","year":"2012"},{"key":"bibr31-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1142\/S0219525912500798"},{"key":"bibr32-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2538961"},{"key":"bibr33-1059712320922916","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00039"},{"key":"bibr34-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1_14"},{"key":"bibr35-1059712320922916","doi-asserted-by":"crossref","unstructured":"Schmerling M., Schillaci G., Hafner V. V. (2015). Goal-directed learning of hand-eye coordination in a humanoid robot. In 2015 joint IEEE international conference on development and learning and epigenetic robotics (ICDL-EpiRob) (pp. 168\u2013175). https:\/\/doi.org\/10.1109\/DEVLRN.2015.7346136","DOI":"10.1109\/DEVLRN.2015.7346136"},{"key":"bibr36-1059712320922916","doi-asserted-by":"crossref","unstructured":"Schoenberger J. L., Frahm J. M. (2016). Structure-from-motion revisited [IEEE conference on computer vision and pattern recognition]. https:\/\/ieeexplore.ieee.org\/document\/7780814","DOI":"10.1109\/CVPR.2016.445"},{"key":"bibr37-1059712320922916","doi-asserted-by":"crossref","unstructured":"Schoenberger J. L., Zheng E., Pollefeys M., Frahm J. M. (2016). Pixelwise view selection for unstructured multi-view stereo [European Conference on Computer Vision]. https:\/\/demuc.de\/papers\/schoenberger2016mvs.pdf","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"bibr38-1059712320922916","volume":"14","author":"Shi M.","year":"2020","journal-title":"Frontiers in Computational Neuroscience"},{"key":"bibr39-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2018.01.033"},{"key":"bibr40-1059712320922916","doi-asserted-by":"crossref","unstructured":"Tschantz A., Seth A. K., Buckley C. L. (2019). Learning action-oriented models through active inference. Biorxiv. https:\/\/www.biorxiv.org\/content\/10.1101\/764969v1","DOI":"10.1101\/764969"},{"key":"bibr41-1059712320922916","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0080876"}],"container-title":["Adaptive Behavior"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1059712320922916","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1059712320922916","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1059712320922916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T16:19:04Z","timestamp":1777393144000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1059712320922916"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,7]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["10.1177\/1059712320922916"],"URL":"https:\/\/doi.org\/10.1177\/1059712320922916","relation":{},"ISSN":["1059-7123","1741-2633"],"issn-type":[{"value":"1059-7123","type":"print"},{"value":"1741-2633","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,7]]}}}