{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T10:52:32Z","timestamp":1762253552775,"version":"3.28.0"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1109\/ro-man47096.2020.9223451","type":"proceedings-article","created":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T15:56:21Z","timestamp":1602690981000},"page":"612-617","source":"Crossref","is-referenced-by-count":5,"title":["Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies"],"prefix":"10.1109","author":[{"given":"Remi","family":"Dromnelle","sequence":"first","affiliation":[{"name":"Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France"}]},{"given":"Benoit","family":"Girard","sequence":"additional","affiliation":[{"name":"Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France"}]},{"given":"Erwan","family":"Renaudo","sequence":"additional","affiliation":[{"name":"Universitat Innsbruck,Intelligent and Interactive Systems Group,Innsbruck,Austria"}]},{"given":"Raja","family":"Chatila","sequence":"additional","affiliation":[{"name":"Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France"}]},{"given":"Mehdi","family":"Khamassi","sequence":"additional","affiliation":[{"name":"Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Shaping Robot Behaviour with Unlabeled Human Instructions","volume-title":"PhD thesis","author":"Najar","year":"2017"},{"key":"ref2","article-title":"Teaching with rewards and punishments: Reinforcement or communication?","author":"Ho","year":"2015","journal-title":"CogSci"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2307\/1126732"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms9096"},{"key":"ref5","first-page":"5","article-title":"Combining manual feedback with subsequent mdp reward signals for reinforcement learning","volume-title":"Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1-Volume 1","author":"Knox"},{"key":"ref6","first-page":"2625","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","author":"Griffith","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Intrinsically Motivated and Interactive Reinforcement Learning: a Developmental Approach","volume-title":"PhD thesis","author":"Fournier","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64313-3_8"},{"key":"ref10","article-title":"On three-layer architectures","author":"Gat","year":"1998","journal-title":"Artificial Intelligence and Mobile Robots"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/027836499801700402"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nn1560"},{"issue":"225","key":"ref13","article-title":"Modelling choice and reaction time during arbitrary visuomotor learning through the coordination of adaptive working memory and reinforcement learning","volume":"9","author":"Viejo","year":"2015","journal-title":"Frontiers in Behavioral Neuroscience"},{"journal-title":"Pareto Analysis.","year":"2015","author":"Powell","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/bfb0027307"},{"key":"ref16","article-title":"Reinforcement learning from simultaneous human and mdp reward","author":"Knox","year":"2012","journal-title":"AAMAS"}],"event":{"name":"2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2020,8,31]]},"location":"Naples, Italy","end":{"date-parts":[[2020,9,4]]}},"container-title":["2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9219088\/9223329\/09223451.pdf?arnumber=9223451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T20:37:35Z","timestamp":1706042255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9223451\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/ro-man47096.2020.9223451","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}