{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T10:00:55Z","timestamp":1781863255770,"version":"3.54.5"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"22","license":[{"start":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T00:00:00Z","timestamp":1693958400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T00:00:00Z","timestamp":1693958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"ANR MIAI institute","award":["ANR-19-P3IA-0003)"],"award-info":[{"award-number":["ANR-19-P3IA-0003)"]}]},{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["SPRING (#871245)"],"award-info":[{"award-number":["SPRING (#871245)"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ANR ML3RI","award":["ANR-19-CE33-0008-01"],"award-info":[{"award-number":["ANR-19-CE33-0008-01"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s10489-023-04691-5","type":"journal-article","created":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T04:01:36Z","timestamp":1693972896000},"page":"27249-27268","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Variational meta reinforcement learning for social robotics"],"prefix":"10.1007","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1041-3632","authenticated-orcid":false,"given":"Anand","family":"Ballou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5354-1084","authenticated-orcid":false,"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2368-521X","authenticated-orcid":false,"given":"Chris","family":"Reinke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,9,6]]},"reference":[{"issue":"3\u20134","key":"4691_CR1","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/S0921-8890(02)00372-X","volume":"42","author":"T Fong","year":"2003","unstructured":"Fong T, Nourbakhsh I, Dautenhahn K (2003) A survey of socially interactive robots. Robotics and autonomous systems. 42(3\u20134):143\u201366","journal-title":"Robotics and autonomous systems."},{"key":"4691_CR2","doi-asserted-by":"publisher","first-page":"7107","DOI":"10.1109\/TII.2022.3143605","volume":"18","author":"H Liu","year":"2022","unstructured":"Liu H, Liu T, Zhang Z, Sangaiah A, Yang B, Li YA (2022) Asymmetric Relation-Aware Representation Learning for Head Pose Estimation in Industrial Human-Computer Interaction. IEEE Transactions on Industrial Informatics. 18:7107\u201317","journal-title":"IEEE Transactions on Industrial Informatics."},{"key":"4691_CR3","doi-asserted-by":"crossref","unstructured":"Davison DP, Wijnen FM, Charisi V, van\u00a0der Meij J, Evers V, Reidsma D. Working with a social robot in school: a long-term real-world unsupervised deployment. In: ACM\/IEEE international conference on human-robot interaction; 2020. p. 63-72","DOI":"10.1145\/3319502.3374803"},{"key":"4691_CR4","doi-asserted-by":"crossref","unstructured":"Kubota A, Peterson EI, Rajendren V, Kress-Gazit H, Riek LD. Jessie: Synthesizing social robot behaviors for personalized neurorehabilitation and beyond. In: ACM\/IEEE international conference on human-robot interaction; 2020. p. 121-30","DOI":"10.1145\/3319502.3374836"},{"key":"4691_CR5","doi-asserted-by":"crossref","unstructured":"Colledanchise M, \u00d6gren P. Behavior trees in robotics and AI: An introduction. CRC Press; 2018","DOI":"10.1201\/9780429489105"},{"key":"4691_CR6","unstructured":"Sutton RS, Barto AG. Reinforcement learning: An introduction. MIT press; 2018"},{"issue":"4","key":"4691_CR7","doi-asserted-by":"publisher","first-page":"1292","DOI":"10.3390\/s21041292","volume":"21","author":"N Akalin","year":"2021","unstructured":"Akalin N, Loutfi A (2021) Reinforcement learning approaches in social robotics. Sensors. 21(4):1292","journal-title":"Sensors."},{"key":"4691_CR8","unstructured":"Beck J, Vuorio R, Liu EZ, Xiong Z, Zintgraf L, Finn C et\u00a0al (2023) A Survey of Meta-Reinforcement Learning. arXiv preprint arXiv:2301.08028"},{"key":"4691_CR9","doi-asserted-by":"crossref","unstructured":"Chen YF, Liu M, Everett M, How JP. Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning. In: IEEE International Conference on Robotics and Automation; 2017. p. 285-92","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"4691_CR10","doi-asserted-by":"crossref","unstructured":"Zhou Z, Zhu P, Zeng Z, Xiao J, Lu H, Zhou Z. Robot navigation in a crowd by integrating deep reinforcement learning and online planning. Applied Intelligence. 2022:1-17","DOI":"10.1007\/s10489-022-03191-2"},{"key":"4691_CR11","unstructured":"Li C, Castellano G, Gao Y. Efficient Learning of Socially Aware Robot Approaching Behavior Toward Groups via Meta-Reinforcement Learning. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems; 2020. p. 12156-9"},{"key":"4691_CR12","unstructured":"Kingma DP, Welling M. Auto-encoding variational bayes. In: International Conference on Learning Representatnions; 2014."},{"key":"4691_CR13","unstructured":"Rakelly K, Zhou A, Finn C, Levine S, Quillen D. Efficient off-policy meta-reinforcement learning via probabilistic context variables. In: International conference on machine learning; 2019. p. 5331-40"},{"key":"4691_CR14","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1016\/j.neucom.2020.12.090","volume":"436","author":"T Liu","year":"2021","unstructured":"Liu T, Wang J, Yang B, Wang X (2021) NGDNet: Nonuniform Gaussian-label distribution learning for infrared head pose estimation and on-task behavior understanding in the classroom. Neurocomputing. 436:210\u201320","journal-title":"Neurocomputing."},{"issue":"1\u20132","key":"4691_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000089","volume":"15","author":"L Girin","year":"2021","unstructured":"Girin L, Leglaive S, Bie X, Diard J, Hueber T, Alameda-Pineda X (2021) Dynamical Variational Autoencoders: A Comprehensive Review. Foundations and Trends in Machine Learning. 15(1\u20132):1\u2013175","journal-title":"Foundations and Trends in Machine Learning."},{"key":"4691_CR16","unstructured":"Broomhead DS, Lowe D. Radial basis functions, multi-variable functional interpolation and adaptive networks. Royal Signals and Radar Establishment Malvern; 1988"},{"issue":"2","key":"4691_CR17","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1162\/neco.1991.3.2.246","volume":"3","author":"J Park","year":"1991","unstructured":"Park J, Sandberg IW (1991) Universal approximation using radial-basis-function networks. Neural computation. 3(2):246\u201357","journal-title":"Neural computation."},{"key":"4691_CR18","doi-asserted-by":"crossref","unstructured":"Vidnerov\u00e1 P, Neruda R. Deep networks with rbf layers to prevent adversarial examples. In: Artificial Intelligence and Soft Computing. Springer; 2018. p. 257-66","DOI":"10.1007\/978-3-319-91253-0_25"},{"key":"4691_CR19","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.csda.2018.08.015","volume":"131","author":"S Abpeykar","year":"2019","unstructured":"Abpeykar S, Ghatee M, Zare H (2019) Ensemble decision forest of RBF networks via hybrid feature clustering approach for high-dimensional data classification. Computational Statistics & Data Analysis. 131:12\u201336","journal-title":"Computational Statistics & Data Analysis."},{"key":"4691_CR20","doi-asserted-by":"crossref","unstructured":"Asadi K, Parikh N, Parr RE, Konidaris GD, Littman ML. Deep radial-basis value functions for continuous control. In: AAAI Conference on Artificial Intelligence. vol.\u00a035; 2021. p. 6696-704","DOI":"10.1609\/aaai.v35i8.16828"},{"key":"4691_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103837","volume":"145","author":"R M\u00f6ller","year":"2021","unstructured":"M\u00f6ller R, Furnari A, Battiato S, H\u00e4rm\u00e4 A, Farinella GM (2021) A survey on human-aware robot navigation. Robotics and Autonomous Systems. 145:103837","journal-title":"Robotics and Autonomous Systems."},{"key":"4691_CR22","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.patrec.2018.05.023","volume":"118","author":"S Lathuili\u00e8re","year":"2019","unstructured":"Lathuili\u00e8re S, Mass\u00e9 B, Mesejo P, Horaud R (2019) Neural network based reinforcement learning for audio-visual gaze control in human-robot interaction. Pattern Recognition Letters. 118:61\u201371","journal-title":"Pattern Recognition Letters."},{"key":"4691_CR23","doi-asserted-by":"crossref","unstructured":"Breazeal C, Dautenhahn K, Kanda T. Social robotics. Springer handbook of robotics. 2016:1935-72","DOI":"10.1007\/978-3-319-32552-1_72"},{"key":"4691_CR24","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.copsyc.2020.01.003","volume":"36","author":"TB Sheridan","year":"2020","unstructured":"Sheridan TB (2020) A review of recent research in social robotics. Current opinion in psychology. 36:7\u201312","journal-title":"Current opinion in psychology."},{"key":"4691_CR25","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s43154-020-00035-0","volume":"2","author":"A Henschel","year":"2021","unstructured":"Henschel A, Laban G, Cross ES (2021) What makes a robot social? a review of social robots from science fiction to a home or hospital near you. Current Robotics Reports. 2:9\u201319","journal-title":"Current Robotics Reports."},{"issue":"3","key":"4691_CR26","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3390\/mti1030014","volume":"1","author":"MI Ahmad","year":"2017","unstructured":"Ahmad MI, Mubin O, Orlando J (2017) A systematic review of adaptivity in human-robot interaction. Multimodal Technologies and Interaction. 1(3):14","journal-title":"Multimodal Technologies and Interaction."},{"key":"4691_CR27","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/s12369-018-0485-4","volume":"11","author":"GS Martins","year":"2019","unstructured":"Martins GS, Santos L, Dias J (2019) User-adaptive interaction in social robots: A survey focusing on non-physical interaction. International Journal of Social Robotics. 11:185\u2013205","journal-title":"International Journal of Social Robotics."},{"issue":"3","key":"4691_CR28","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3390\/robotics8030054","volume":"8","author":"O Nocentini","year":"2019","unstructured":"Nocentini O, Fiorini L, Acerbi G, Sorrentino A, Mancioppi G, Cavallo F (2019) A survey of behavioral models for social robots. Robotics. 8(3):54","journal-title":"Robotics."},{"key":"4691_CR29","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/s12369-019-00560-9","volume":"12","author":"P Patompak","year":"2020","unstructured":"Patompak P, Jeong S, Nilkhamhang I, Chong NY (2020) Learning proxemics for personalized human-robot social interaction. International Journal of Social Robotics. 12:267\u201380","journal-title":"International Journal of Social Robotics."},{"key":"4691_CR30","doi-asserted-by":"crossref","unstructured":"Choi J, Dance C, Kim Je, Park Ks, Han J, Seo J, et\u00a0al. Fast adaptation of deep reinforcement learning-based navigation skills to human preference. In: IEEE International Conference on Robotics and Automation; 2020. p. 3363-70","DOI":"10.1109\/ICRA40945.2020.9197159"},{"key":"4691_CR31","first-page":"1060","volume":"33","author":"J Oh","year":"2020","unstructured":"Oh J, Hessel M, Czarnecki WM, Xu Z, van Hasselt HP, Singh S et al (2020) Discovering reinforcement learning algorithms. Advances in Neural Information Processing Systems. 33:1060\u201370","journal-title":"Advances in Neural Information Processing Systems."},{"key":"4691_CR32","unstructured":"Kirsch L, van Steenkiste S, Schmidhuber J. Improving generalization in meta reinforcement learning using learned objectives. In: International Conference on Learning Representations; 2020."},{"key":"4691_CR33","unstructured":"Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning; 2017. p. 1126-35"},{"key":"4691_CR34","unstructured":"Duan Y, Schulman J, Chen X, Bartlett PL, Sutskever I, Abbeel P (2016) Fast reinforcement learning via slow reinforcement learning. arXiv preprint arXiv:1611.02779"},{"key":"4691_CR35","unstructured":"Zhao Z, Nagabandi A, Rakelly K, Finn C, Levine S. MELD: Meta-Reinforcement Learning from Images via Latent State Models. In: Conference on Robot Learning; 2021. p. 1246-61"},{"key":"4691_CR36","unstructured":"Dai B, Wang Z, Wipf D. The usual suspects? Reassessing blame for VAE posterior collapse. In: International Conference on Machine Learning; 2020. p. 2313-22"},{"key":"4691_CR37","unstructured":"Zhao S, Song J, Ermon S (2017) Infovae: Information maximizing variational autoencoders. arXiv preprint arXiv:1706.02262"},{"key":"4691_CR38","unstructured":"Razavi A, van\u00a0den Oord A, Poole B, Vinyals O. Preventing Posterior Collapse with delta-VAEs. In: International Conference on Learning Representations; 2019"},{"key":"4691_CR39","unstructured":"S\u00f8nderby CK, Raiko T, Maal\u00f8e L, S\u00f8nderby SK, Winther O. Ladder variational autoencoders. In: Advances in neural information processing systems; 2016."},{"key":"4691_CR40","unstructured":"Huang CW, Tan S, Lacoste A, Courville AC. Improving explorability in variational inference with annealed variational objectives. In: Advances in neural information processing systems; 2018."},{"key":"4691_CR41","unstructured":"Reinke C, Etcheverry M, Oudeyer PY. Intrinsically motivated exploration for automated discovery of patterns in morphogenetic systems. In: International Conference on Learning Representations; 2020."},{"key":"4691_CR42","unstructured":"He J, Spokoyny D, Neubig G, Berg-Kirkpatrick T. Lagging Inference Networks and Posterior Collapse in Variational Autoencoders. In: International Conference on Learning Representations; 2019."},{"key":"4691_CR43","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning; 2018."},{"key":"4691_CR44","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D et\u00a0al (2013) Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602"},{"key":"4691_CR45","unstructured":"GitHub (2019) Garage: A toolkit for reproducible reinforcement learning research. https:\/\/github.com\/rlworkgroup\/garage"},{"key":"4691_CR46","doi-asserted-by":"crossref","unstructured":"Pedica C, Vilhj\u00e1lmsson H. Social perception and steering for online avatars. In: International Workshop on Intelligent Virtual Agents. Springer; 2008. p. 104-16","DOI":"10.1007\/978-3-540-85483-8_11"},{"issue":"2","key":"4691_CR47","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1109\/TRO.2012.2226387","volume":"29","author":"S Satake","year":"2012","unstructured":"Satake S, Kanda T, Glas DF, Imai M, Ishiguro H, Hagita N (2012) A robot that approaches pedestrians. IEEE Transactions on Robotics. 29(2):508\u201324","journal-title":"IEEE Transactions on Robotics."},{"key":"4691_CR48","unstructured":"Reinke C, Alameda-Pineda X (2023) Successor feature representations. Transactions on Machine Learning Research"},{"key":"4691_CR49","doi-asserted-by":"crossref","unstructured":"Quintero-Pena C, Chamzas C, Sun Z, Unhelkar V, Kavraki LE. Human-Guided Motion Planning in Partially Observable Environments. In: IEEE International Conference on Robotics and Automation; 2022. p. 7226-32","DOI":"10.1109\/ICRA46639.2022.9811893"},{"key":"4691_CR50","doi-asserted-by":"crossref","unstructured":"Rosano M, Furnari A, Gulino L, Farinella GM. On embodied visual navigation in real environments through habitat. In: IAPR International Conference on Pattern Recognition; 2021. p. 9740-7","DOI":"10.1109\/ICPR48806.2021.9413026"},{"key":"4691_CR51","doi-asserted-by":"crossref","unstructured":"Wortsman M, Ehsani K, Rastegari M, Farhadi A, Mottaghi R. Learning to learn how to learn: Self-adaptive visual navigation using meta-learning. In: IEEE\/CVF conference on computer vision and pattern recognition; 2019. p. 6750-9","DOI":"10.1109\/CVPR.2019.00691"},{"key":"4691_CR52","doi-asserted-by":"crossref","unstructured":"Arndt K, Hazara M, Ghadirzadeh A, Kyrki V. Meta reinforcement learning for sim-to-real domain adaptation. In: IEEE international conference on robotics and automation; 2020. p. 2725-31","DOI":"10.1109\/ICRA40945.2020.9196540"},{"key":"4691_CR53","doi-asserted-by":"crossref","unstructured":"Yang Q, Sim\u00e3o TD, Tindemans SH, Spaan MT. WCSAC: Worst-case soft actor critic for safety-constrained reinforcement learning. In: AAAI Conference on Artificial Intelligence; 2021. p. 10639-46","DOI":"10.1609\/aaai.v35i12.17272"},{"key":"4691_CR54","doi-asserted-by":"crossref","unstructured":"L\u00fctjens B, Everett M, How JP. Safe reinforcement learning with model uncertainty estimates. In: International Conference on Robotics and Automation; 2019. p. 8662-8","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"4691_CR55","unstructured":"Xiong Z, Agarwal I, Jagannathan S. HiSaRL: A Hierarchical Framework for Safe Reinforcement Learning. In: SafeAI@ AAAI; 2022."},{"key":"4691_CR56","doi-asserted-by":"crossref","unstructured":"Chen B, Liu Z, Zhu J, Xu M, Ding W, Li L, et\u00a0al. Context-aware safe reinforcement learning for non-stationary environments. In: IEEE International Conference on Robotics and Automation; 2021. p. 10689-95","DOI":"10.1109\/ICRA48506.2021.9561593"},{"key":"4691_CR57","doi-asserted-by":"crossref","unstructured":"Everett M, Chen YF, How JP. Motion planning among dynamic, decision-making agents with deep reinforcement learning. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems; 2018. p. 3052-9","DOI":"10.1109\/IROS.2018.8593871"},{"issue":"2","key":"4691_CR58","doi-asserted-by":"publisher","first-page":"3221","DOI":"10.1109\/LRA.2020.2974695","volume":"5","author":"SH Semnani","year":"2020","unstructured":"Semnani SH, Liu H, Everett M, De Ruiter A, How JP (2020) Multi-agent motion planning for dense and dynamic environments via deep reinforcement learning. IEEE Robotics and Automation Letters. 5(2):3221\u20136","journal-title":"IEEE Robotics and Automation Letters."},{"key":"4691_CR59","unstructured":"Charakorn R, Manoonpong P, Dilokthanakul N. Learning to Cooperate with Unseen Agents Through Meta-Reinforcement Learning. In: International Conference on Autonomous Agents and MultiAgent Systems; 2021. p. 1478-9"},{"key":"4691_CR60","unstructured":"He JZY, Erickson Z, Brown DS, Raghunathan A, Dragan A. Learning Representations that Enable Generalization in Assistive Tasks. In: Conference on Robot Learning; 2023. p. 2105-14"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-04691-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-023-04691-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-04691-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T14:55:46Z","timestamp":1730040946000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-023-04691-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,6]]},"references-count":60,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["4691"],"URL":"https:\/\/doi.org\/10.1007\/s10489-023-04691-5","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,6]]},"assertion":[{"value":"4 May 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}