{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T21:37:00Z","timestamp":1791409020754,"version":"4.3.3"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s10514-023-10109-5","type":"journal-article","created":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T06:02:10Z","timestamp":1686981730000},"page":"771-796","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Learning latent representations to co-adapt to humans"],"prefix":"10.1007","volume":"47","author":[{"given":"Sagar","family":"Parekh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dylan P.","family":"Losey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,17]]},"reference":[{"key":"10109_CR1","unstructured":"Small Business Economic Profile. (2020). US Small Business Administration."},{"issue":"2","key":"10109_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/app12020937","volume":"12","author":"J Arents","year":"2022","unstructured":"Arents, J., & Greitans, M. (2022). Smart industrial robot control trends: Challenges and opportunities within manufacturing. Applied Sciences, 12(2), 1.","journal-title":"Applied Sciences"},{"issue":"1","key":"10109_CR3","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/LRA.2020.3028049","volume":"6","author":"A Bajcsy","year":"2020","unstructured":"Bajcsy, A., Bansal, S., Ratner, E., Tomlin, C. J., & Dragan, A. D. (2020). A robust control framework for human motion prediction. IEEE Robotics and Automation Letters, 6(1), 24\u201331.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10109_CR4","unstructured":"Baker, C., Saxe, R., & Tenenbaum, J. (2011). Bayesian theory of mind: Modeling joint belief-desire attribution. In Proceedings of the annual meeting of the cognitive science society (Vol.\u00a033)."},{"key":"10109_CR5","doi-asserted-by":"crossref","unstructured":"Bandyopadhyay, T., Won, K.S., Frazzoli, E., Hsu, D., Lee, W.S., & Rus, D. (2013). Intention-aware motion planning. In Algorithmic foundations of robotics (pp. 475\u2013491). Springer.","DOI":"10.1007\/978-3-642-36279-8_29"},{"key":"10109_CR6","doi-asserted-by":"crossref","unstructured":"Bestick, A., Bajcsy, R., & Dragan, A. D. (2016). Implicitly assisting humans to choose good grasps in robot to human handovers. In International symposium on experimental robotics (pp. 341\u2013354).","DOI":"10.1007\/978-3-319-50115-4_30"},{"key":"10109_CR7","unstructured":"Cao, K., Lazaridou, A., Lanctot, M., Leibo, J.Z., Tuyls, K., & Clark, S. (2018). Emergent communication through negotiation. In International conference on learning representations."},{"key":"10109_CR8","first-page":"1","volume":"32","author":"M Carroll","year":"2019","unstructured":"Carroll, M., Shah, R., Ho, M. K., Griffiths, T., Seshia, S., Abbeel, P., & Dragan, A. (2019). On the utility of learning about humans for human\u2013AI coordination. Advances in Neural Information Processing Systems, 32, 1.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10109_CR9","unstructured":"Ch\u00e9rief-Abdellatif, B. E., Shi, Y., Doucet, A., & Guedj, B. (2022). On PAC-Bayesian reconstruction guarantees for VAEs. In International conference on artificial intelligence and statistics (pp. 3066\u20133079)."},{"key":"10109_CR10","first-page":"10707","volume":"33","author":"F Christianos","year":"2020","unstructured":"Christianos, F., Sch\u00e4fer, L., & Albrecht, S. (2020). Shared experience actor-critic for multi-agent reinforcement learning. Advances in Neural Information Processing Systems, 33, 10707\u201310717.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10109_CR11","first-page":"1","volume":"29","author":"J Foerster","year":"2016","unstructured":"Foerster, J., Assael, I. A., De Freitas, N., & Whiteson, S. (2016). Learning to communicate with deep multi-agent reinforcement learning. Advances in Neural Information Processing Systems, 29, 1.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10109_CR12","unstructured":"Foerster, J., Chen, R. Y., Al-Shedivat, M., Whiteson, S., Abbeel, P., & Mordatch, I. (2018). Learning with opponent-learning awareness. In International conference on autonomous agents and multiagent systems (pp. 122\u2013130)."},{"key":"10109_CR13","doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., & Whiteson, S. (2018). Counterfactual multi-agent policy gradients. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"10109_CR14","doi-asserted-by":"crossref","unstructured":"Germain, P., Lacasse, A., Laviolette, F., Marchand, M. (2009). PAC-Bayesian learning of linear classifiers. In International Conference on Machine Learning (pp. 353\u2013360).","DOI":"10.1145\/1553374.1553419"},{"issue":"3","key":"10109_CR15","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1561\/1100000005","volume":"1","author":"MA Goodrich","year":"2008","unstructured":"Goodrich, M. A., & Schultz, A. C. (2008). Human\u2013robot interaction: A survey. Foundations and Trends in Human\u2013Computer Interaction, 1(3), 203\u2013275.","journal-title":"Foundations and Trends in Human\u2013Computer Interaction"},{"key":"10109_CR16","doi-asserted-by":"crossref","unstructured":"Gualtieri, L., Palomba, I., Wehrle, E. J., & Vidoni, R. (2020). The opportunities and challenges of SME manufacturing automation: Safety and ergonomics in human\u2013robot collaboration. Industry 4.0 for SMEs (pp. 105\u2013144).","DOI":"10.1007\/978-3-030-25425-4_4"},{"key":"10109_CR17","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., & Levine, S. (2018). Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning."},{"key":"10109_CR18","unstructured":"Hernandez-Leal, P., Kaisers, M., Baarslag, T., & de\u00a0Cote, E. M. (2017). A survey of learning in multiagent environments: Dealing with non-stationarity. arXiv preprint arXiv:1707.09183."},{"key":"10109_CR19","doi-asserted-by":"crossref","unstructured":"Hu, H., & Fisac, J. F. (2022). Active uncertainty learning for human\u2013robot interaction: An implicit dual control approach. Workshop on the Algorithmic Foundations of Robotics.","DOI":"10.1007\/978-3-031-21090-7_23"},{"key":"10109_CR20","unstructured":"Huang, Z., Mun, Y.J., Li, X., Xie, Y., Zhong, N., Liang, W., Geng, J., Chen, T., & Driggs-Campbell, K. (2022). Seamless interaction design with coexistence and cooperation modes for robust human\u2013robot collaboration. arXiv preprint arXiv:2206.01775."},{"issue":"4","key":"10109_CR21","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/MRA.2011.2181676","volume":"19","author":"S Ikemoto","year":"2012","unstructured":"Ikemoto, S., Amor, H. B., Minato, T., Jung, B., & Ishiguro, H. (2012). Physical human\u2013robot interaction: Mutual learning and adaptation. IEEE Robotics & Automation Magazine, 19(4), 24\u201335.","journal-title":"IEEE Robotics & Automation Magazine"},{"issue":"6443","key":"10109_CR22","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1126\/science.aau6249","volume":"364","author":"M Jaderberg","year":"2019","unstructured":"Jaderberg, M., Czarnecki, W. M., Dunning, I., Marris, L., Lever, G., Castaneda, A. G., Beattie, C., Rabinowitz, N. C., Morcos, A. S., & Ruderman, A. (2019). Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science, 364(6443), 859\u2013865.","journal-title":"Science"},{"key":"10109_CR23","unstructured":"Jaques, N., Lazaridou, A., Hughes, E., Gulcehre, C., Ortega, P., Strouse, D., Leibo, J. Z., De\u00a0Freitas, N. (2019). Social influence as intrinsic motivation for multi-agent deep reinforcement learning. In International conference on machine learning (pp. 3040\u20133049)."},{"key":"10109_CR24","first-page":"4415","volume":"33","author":"HJ Jeon","year":"2020","unstructured":"Jeon, H. J., Milli, S., & Dragan, A. (2020). Reward-rational (implicit) choice: A unifying formalism for reward learning. Advances in Neural Information Processing Systems, 33, 4415\u20134426.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10109_CR25","unstructured":"Langford, J., & Shawe-Taylor, J. (2002). PAC-Bayes & margins. In Advances in neural information processing systems (Vol.\u00a015)."},{"issue":"7","key":"10109_CR26","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1007\/s10514-021-10016-7","volume":"45","author":"M Li","year":"2021","unstructured":"Li, M., Kwon, M., & Sadigh, D. (2021). Influencing leading and following in human\u2013robot teams. Autonomous Robots, 45(7), 959\u2013978.","journal-title":"Autonomous Robots"},{"key":"10109_CR27","doi-asserted-by":"crossref","unstructured":"Li, S., Figueroa, N., Shah, A. J., & Shah, J.A. (2021). Provably safe and efficient motion planning with uncertain human dynamics. In Robotics: Science and systems.","DOI":"10.15607\/RSS.2021.XVII.050"},{"key":"10109_CR28","unstructured":"Losey, D. P., Li, M., Bohg, J., & Sadigh, D. (2020). Learning from my partner\u2019s actions: Roles in decentralized robot teams. In Conference on robot learning (pp. 752\u2013765)."},{"key":"10109_CR29","first-page":"1","volume":"30","author":"R Lowe","year":"2017","unstructured":"Lowe, R., Wu, Y. I., Tamar, A., Harb, J., Pieter Abbeel, O., & Mordatch, I. (2017). Multi-agent actor-critic for mixed cooperative-competitive environments. Advances in Neural Information Processing Systems, 30, 1.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10109_CR30","unstructured":"Lu, C., Willi, T., De\u00a0Witt, C.A.S., Foerster, J. (2022). Model-free opponent shaping. In International Conference on Machine Learning (pp. 14398\u201314411)."},{"issue":"2\u20133","key":"10109_CR31","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1177\/0278364920959444","volume":"40","author":"A Majumdar","year":"2021","unstructured":"Majumdar, A., Farid, A., & Sonar, A. (2021). PAC-Bayes control: Learning policies that provably generalize to novel environments. The International Journal of Robotics Research, 40(2\u20133), 574\u2013593.","journal-title":"The International Journal of Robotics Research"},{"key":"10109_CR32","unstructured":"Majumdar, A., Goldstein, M. (2018). PAC-Bayes control: Synthesizing controllers that provably generalize to novel environments. In Conference on Robot Learning (pp. 293\u2013305)."},{"issue":"4","key":"10109_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/robotics8040100","volume":"8","author":"E Matheson","year":"2019","unstructured":"Matheson, E., Minto, R., Zampieri, E. G., Faccio, M., & Rosati, G. (2019). Human\u2013robot collaboration in manufacturing applications: A review. Robotics, 8(4), 1.","journal-title":"Robotics"},{"key":"10109_CR34","unstructured":"Maurer, A. (2004). A note on the PAC-Bayesian theorem. arXiv preprint arXiv: cs\/0411099."},{"issue":"3","key":"10109_CR35","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1023\/A:1007618624809","volume":"37","author":"DA McAllester","year":"1999","unstructured":"McAllester, D. A. (1999). Some PAC-Bayesian theorems. Machine Learning, 37(3), 355\u2013363.","journal-title":"Machine Learning"},{"key":"10109_CR36","unstructured":"Ndousse, K. K., Eck, D., Levine, S., & Jaques, N. (2021). Emergent social learning via multi-agent reinforcement learning. In International conference on machine learning (pp. 7991\u20138004)."},{"key":"10109_CR37","first-page":"1","volume":"30","author":"B Neyshabur","year":"2017","unstructured":"Neyshabur, B., Bhojanapalli, S., McAllester, D., & Srebro, N. (2017). Exploring generalization in deep learning. Advances in Neural Information Processing Systems, 30, 1.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"5\u20137","key":"10109_CR38","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1177\/0278364917690593","volume":"36","author":"S Nikolaidis","year":"2017","unstructured":"Nikolaidis, S., Hsu, D., & Srinivasa, S. (2017). Human-robot mutual adaptation in collaborative tasks: Models and experiments. The International Journal of Robotics Research, 36(5\u20137), 618\u2013634.","journal-title":"The International Journal of Robotics Research"},{"key":"10109_CR39","doi-asserted-by":"crossref","unstructured":"Nikolaidis, S., Nath, S., Procaccia, A. D., & Srinivasa, S. (2017). Game-theoretic modeling of human adaptation in human\u2013robot collaboration. In ACM\/IEEE international conference on human\u2013robot interaction (pp. 323\u2013331).","DOI":"10.1145\/2909824.3020253"},{"key":"10109_CR40","unstructured":"Nikolaidis, S., Ramakrishnan, R., Gu, K., & Shah, J. Efficient model learning from joint-action demonstrations for human\u2013robot collaborative tasks. In Proceedings of the 10th annual ACM\/IEEE international conference on human\u2013robot interaction."},{"issue":"2","key":"10109_CR41","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1109\/LRA.2020.3048660","volume":"6","author":"H Nishimura","year":"2021","unstructured":"Nishimura, H., Mehr, N., Gaidon, A., & Schwager, M. (2021). RAT iLQR: A risk auto-tuning controller to optimally account for stochastic model mismatch. IEEE Robotics and Automation Letters, 6(2), 763\u2013770.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10109_CR42","doi-asserted-by":"crossref","unstructured":"Parekh, S., Habibian, S., Losey, D.P. (2022). RILI: Robustly influencing latent intent. In IEEE\/RSJ international conference on intelligent robots and systems.","DOI":"10.1109\/IROS47612.2022.9981601"},{"issue":"1","key":"10109_CR43","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/MRA.2018.2879747","volume":"26","author":"A Perzylo","year":"2019","unstructured":"Perzylo, A., Rickert, M., Kahl, B., Somani, N., Lehmann, C., Kuss, A., Profanter, S., Beck, A. B., Haage, M., Hansen, M. R., et al. (2019). SMErobotics: Smart robots for flexible manufacturing. IEEE Robotics & Automation Magazine, 26(1), 78\u201390.","journal-title":"IEEE Robotics & Automation Magazine"},{"key":"10109_CR44","unstructured":"Raileanu, R., Denton, E., Szlam, A., Fergus, R. (2018). Modeling others using oneself in multi-agent reinforcement learning. In International Conference on Machine Learning (pp. 4257\u20134266)."},{"key":"10109_CR45","doi-asserted-by":"crossref","unstructured":"Rubinstein, A. (1998). Modeling Bounded Rationality. MIT Press.","DOI":"10.7551\/mitpress\/4702.001.0001"},{"key":"10109_CR46","unstructured":"Sadigh, D., Sastry, S., Seshia, S. A., & Dragan, A. D. (2016). Planning for autonomous cars that leverage effects on human actions. In Robotics: Science and systems."},{"key":"10109_CR47","doi-asserted-by":"crossref","unstructured":"Sagheb, S., Mun, Y. J., Ahmadian, N., Christie, B. A., Bajcsy, A., Driggs-Campbell, K., Losey, D. P. (2022). Towards robots that influence humans over long-term interaction. arXiv preprint arXiv:2209.10588.","DOI":"10.1109\/ICRA48891.2023.10160321"},{"issue":"3","key":"10109_CR48","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1561\/2300000065","volume":"8","author":"L Sanneman","year":"2021","unstructured":"Sanneman, L., Fourie, C., & Shah, J. A. (2021). The state of industrial robotics: Emerging technologies, challenges, and key research directions. Foundations and Trends in Robotics, 8(3), 225\u2013306.","journal-title":"Foundations and Trends in Robotics"},{"key":"10109_CR49","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1162\/153244303765208377","volume":"3","author":"M Seeger","year":"2002","unstructured":"Seeger, M. (2002). PAC-Bayesian generalisation error bounds for gaussian process classification. Journal of Machine Learning Research, 3, 233\u2013269.","journal-title":"Journal of Machine Learning Research"},{"key":"10109_CR50","unstructured":"Shih, A., Ermon, S., Sadigh, D. Conditional imitation learning for multi-agent games. In 17th ACM\/IEEE International Conference on Human\u2013Robot Interaction (HRI)."},{"key":"10109_CR51","unstructured":"Singh, A., Jain, T., Sukhbaatar, S. (2018). Learning when to communicate at scale in multiagent cooperative and competitive tasks. In International conference on learning representations."},{"key":"10109_CR52","first-page":"14502","volume":"34","author":"D Strouse","year":"2021","unstructured":"Strouse, D., McKee, K., Botvinick, M., Hughes, E., & Everett, R. (2021). Collaborating with humans without human data. Advances in Neural Information Processing Systems, 34, 14502\u201314515.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10109_CR53","doi-asserted-by":"crossref","unstructured":"Tian, R., Sun, L., Bajcsy, A., Tomizuka, M., Dragan, A.D. (2022). Safety assurances for human\u2013robot interaction via confidence-aware game-theoretic human models. In IEEE International Conference on Robotics and Automation (pp. 11229\u201311235). IEEE.","DOI":"10.1109\/ICRA46639.2022.9812048"},{"issue":"5","key":"10109_CR54","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1109\/TRA.2002.804040","volume":"18","author":"R Vidal","year":"2002","unstructured":"Vidal, R., Shakernia, O., Kim, H. J., Shim, D. H., & Sastry, S. (2002). Probabilistic pursuit-evasion games: Theory, implementation, and experimental evaluation. IEEE Transactions on Robotics and Automation, 18(5), 662\u2013669.","journal-title":"IEEE Transactions on Robotics and Automation"},{"key":"10109_CR55","doi-asserted-by":"crossref","unstructured":"Von Der\u00a0Osten, F. B., Kirley, M., & Miller, T. (2017). The minds of many: Opponent modeling in a stochastic game. In IJCAI (pp. 3845\u20133851).","DOI":"10.24963\/ijcai.2017\/537"},{"key":"10109_CR56","unstructured":"Wang, W. Z., Shih, A., Xie, A., & Sadigh, D. (2021). Influencing towards stable multi-agent interactions. In Conference on Robot Learning."},{"key":"10109_CR57","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10462-021-10118-9","volume":"1","author":"A Wong","year":"2022","unstructured":"Wong, A., B\u00e4ck, T., Kononova, A. V., & Plaat, A. (2022). Deep multiagent reinforcement learning: Challenges and directions. Artificial Intelligence Review, 1, 1\u201334.","journal-title":"Artificial Intelligence Review"},{"key":"10109_CR58","doi-asserted-by":"crossref","unstructured":"Woodward, M., Finn, C., Hausman, K. (2020). Learning to interactively learn and assist. In AAAI Conference on Artificial Intelligence (Vol.\u00a034, pp. 2535\u20132543).","DOI":"10.1609\/aaai.v34i03.5636"},{"key":"10109_CR59","unstructured":"Xie, A., Losey, D. P., Tolsma, R., Finn, C., & Sadigh, D. (2020). Learning latent representations to influence multi-agent interaction. In Conference on Robot Learning."}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-023-10109-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10514-023-10109-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-023-10109-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T18:04:34Z","timestamp":1690653874000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10514-023-10109-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,17]]},"references-count":59,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["10109"],"URL":"https:\/\/doi.org\/10.1007\/s10514-023-10109-5","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"value":"0929-5593","type":"print"},{"value":"1573-7527","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,17]]},"assertion":[{"value":"16 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All user studies were conducted under university guidelines and followed the protocol of Virginia Tech IRB -755.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Statement"}}]}}