{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T11:11:58Z","timestamp":1762254718976,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"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":[[2023,8,28]]},"DOI":"10.1109\/ro-man57019.2023.10309643","type":"proceedings-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T14:07:48Z","timestamp":1699884468000},"page":"1150-1157","source":"Crossref","is-referenced-by-count":2,"title":["A behavioural transformer for effective collaboration between a robot and a non-stationary human"],"prefix":"10.1109","author":[{"given":"Ruaridh","family":"Mon-Williams","sequence":"first","affiliation":[{"name":"University of Edinburgh,School of Informatics,Edinburgh,U.K,EH8 9AB"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Theodoros","family":"Stouraitis","sequence":"additional","affiliation":[{"name":"Honda Research Institute Europe (HRI-EU),Offenbach am Main,Germany,63073"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sethu","family":"Vijayakumar","sequence":"additional","affiliation":[{"name":"University of Edinburgh,School of Informatics,Edinburgh,U.K,EH8 9AB"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1132","article-title":"Influencing towards stable multi-agent interactions","author":"wang","year":"2022","journal-title":"Conference on Robot Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.01.002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981601"},{"key":"ref30","article-title":"The continuous Bernoulli: Fixing a pervasive error in variational autoencoders","author":"loaiza-ganem","year":"2019","journal-title":"arXiv preprint arXiv 1907 06777"},{"key":"ref11","article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","author":"papoudakis","year":"2019","journal-title":"arXiv preprint arXiv 1906 04329"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2909824.3020252"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2019.00120"},{"key":"ref1","article-title":"Learning Latent Representations to Influence Multi-Agent Interaction","author":"xie","year":"2020","journal-title":"arXiv Tech Rep arXiv 2011 13062"},{"key":"ref17","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv preprint arXiv 1706 03762"},{"key":"ref16","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref19","article-title":"The Boltzmann policy distribution: Accounting for systematic suboptimality in human models","author":"laidlaw","year":"2022","journal-title":"arXiv preprint arXiv 2204 10759"},{"key":"ref18","article-title":"Where do you think you’re going?: Inferring beliefs about dynamics from behavior","author":"reddy","year":"2019","journal-title":"arXiv preprint arXiv 1805 08010"},{"key":"ref24","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"jang","year":"2017","journal-title":"arXiv preprint arXiv 1611 01144"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-9568.2006.05221.x"},{"key":"ref26","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"arXiv preprint arXiv 1801 01000"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054554"},{"key":"ref20","article-title":"Human irrationality: Both bad and good for reward inference","author":"chan","year":"2021","journal-title":"arXiv preprint arXiv 2111 02269"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-91445-5_8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185549"},{"key":"ref28","first-page":"12585","article-title":"CleanRL: High-quality single-file implementations of deep reinforcement learning algorithms","volume":"23","author":"huang","year":"2022","journal-title":"The Journal of Machine Learning Research"},{"key":"ref27","article-title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","author":"papoudakis","year":"2021","journal-title":"arXiv preprint arXiv 2006 07529"},{"key":"ref29","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"arXiv preprint arXiv 1801 01000"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3319502.3374811"},{"key":"ref7","article-title":"Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration","author":"yang","year":"2022","journal-title":"arXiv Tech Rep arXiv 2211 01602"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1109\/TRO.2007.914004","article-title":"Prediction of Human Behavior in Human–Robot Interaction Using Psychological Scales for Anxiety and Negative Attitudes Toward Robots","volume":"24","author":"nomura","year":"2008","journal-title":"IEEE Transactions on Robotics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00221-011-2721-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2992987"},{"key":"ref6","article-title":"Influencing Long-Term Behavior in Multiagent Reinforcement Learning","author":"kim","year":"2022","journal-title":"arXiv Tech Rep arXiv 2203 03535"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.1997.646944"}],"event":{"name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2023,8,28]]},"location":"Busan, Korea, Republic of","end":{"date-parts":[[2023,8,31]]}},"container-title":["2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10309296\/10309265\/10309643.pdf?arnumber=10309643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T11:06:01Z","timestamp":1701255961000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10309643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,28]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ro-man57019.2023.10309643","relation":{},"subject":[],"published":{"date-parts":[[2023,8,28]]}}}