{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T11:18:10Z","timestamp":1753183090029,"version":"3.41.0"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T00:00:00Z","timestamp":1744675200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T00:00:00Z","timestamp":1744675200000},"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":[[2025,6]]},"DOI":"10.1007\/s10514-025-10193-9","type":"journal-article","created":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T18:53:33Z","timestamp":1744743213000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Human2bot: learning zero-shot reward functions for robotic manipulation from human demonstrations"],"prefix":"10.1007","volume":"49","author":[{"given":"Yasir","family":"Salam","sequence":"first","affiliation":[]},{"given":"Yinbei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jonas","family":"Herzog","sequence":"additional","affiliation":[]},{"given":"Jiaqiang","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,15]]},"reference":[{"key":"10193_CR1","doi-asserted-by":"crossref","unstructured":"Alakuijala, M., Dulac-Arnold, G., Mairal, J., Ponce, J. & Schmid, C. (2023). Learning reward functions for robotic manipulation by observing humans. Proceedings of the IEEE international conference on robotics and automation (ICRA)","DOI":"10.1109\/ICRA48891.2023.10161178"},{"key":"10193_CR2","unstructured":"Babaeizadeh, M., Finn, C., Erhan, D., Campbell, R. & Levine, S. (2018). Stochastic variational video prediction. Proceedings of the 6th international conference on learning representations (iclr)"},{"key":"10193_CR3","doi-asserted-by":"publisher","unstructured":"Boer, D., & T, P. (2005). A tutorial on the cross-entropy method. Annals of Operations Research, 134(1), 19\u201367. https:\/\/doi.org\/10.1007\/s10479-005-5724-z","DOI":"10.1007\/s10479-005-5724-z"},{"issue":"2","key":"10193_CR4","doi-asserted-by":"publisher","first-page":"3533","DOI":"10.1109\/LRA.2020.2970490","volume":"5","author":"A Bonardi","year":"2020","unstructured":"Bonardi, A., James, S., & Davison, A. J. (2020). Learning one-shot imitation from humans without humans. IEEE Robotics and Automation Letters, 5(2), 3533\u20133539. https:\/\/doi.org\/10.1109\/LRA.2020.2970490","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10193_CR5","unstructured":"Brown, D.S., Goo, W. & Niekum, S. (2019). Better-than-demonstrator imitation learning via automatically-ranked demonstrations. Proceedings of the 36th international conference on machine learning (icml) (Vol.\u00a097, pp. 783\u2013792). PMLR"},{"key":"10193_CR6","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/s10514-023-10120-w","volume":"47","author":"M Burke","year":"2023","unstructured":"Burke, M., Lu, K., & Angelov, D. (2023). Learning rewards from exploratory demonstrations using probabilistic temporal ranking. Autonomous Robots, 47, 733\u2013751. https:\/\/doi.org\/10.1007\/s10514-023-10120-w","journal-title":"Autonomous Robots"},{"key":"10193_CR7","doi-asserted-by":"crossref","unstructured":"Chane-Sane, E., Schmid, C. & Laptev, I. (2023). Learning video-conditioned policies for unseen manipulation tasks. Proceedings of the ieee international conference on robotics and automation (icra)","DOI":"10.1109\/ICRA48891.2023.10161336"},{"key":"10193_CR8","doi-asserted-by":"crossref","unstructured":"Chen, A.S., Nair, S. & Finn, C. (2021). Learning generalizable robotic reward functions from \u2019in-the-wild\u2019 human videos. Proceedings of robotics: Science and systems (rss)","DOI":"10.15607\/RSS.2021.XVII.012"},{"key":"10193_CR9","unstructured":"Das, N., Bechtle, S., Davchev, T., Jayaraman, D., Rai, A. & Meier, F. (2020). Model-based inverse reinforcement learning from visual demonstrations. Proceedings of the 3rd conference on robot learning (corl) (Vol.\u00a0100, pp. 300\u2013311). PMLR"},{"key":"10193_CR10","unstructured":"Dasari, S., & Gupta, A. (2020). Transformers for one-shot visual imitation. Proceedings of the 3rd conference on robot learning (corl) (Vol.\u00a0100, pp. 99\u2013111). PMLR"},{"key":"10193_CR11","doi-asserted-by":"crossref","unstructured":"DeTone, D., Malisiewicz, T. & Rabinovich, A. (2018). SuperPoint: Self-Supervised Interest Point Detection and Description. Cvpr deep learning for visual slam workshop","DOI":"10.1109\/CVPRW.2018.00060"},{"issue":"3","key":"10193_CR12","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1109\/TRO.2020.3047693","volume":"37","author":"C Eteke","year":"2021","unstructured":"Eteke, C., Kebude, D., & Akgun, B. (2021). Reward learning from very few demonstrations. IEEE Transactions on Robotics, 37(3), 950\u2013966. https:\/\/doi.org\/10.1109\/TRO.2020.3047693","journal-title":"IEEE Transactions on Robotics"},{"key":"10193_CR13","doi-asserted-by":"crossref","unstructured":"Goo, W., & Niekum, S. (2019). One-shot learning of multi-step tasks from observation via activity localization in auxiliary video. Proceedings of the ieee international conference on robotics and automation (icra) (pp. 6551\u20136557)","DOI":"10.1109\/ICRA.2019.8793515"},{"key":"10193_CR14","unstructured":"Goyal, P., Mooney, R.J. & Niekum, S. (2021). Zero-shot task adaptation using natural language. (arXiv preprint arXiv:2106.02972)"},{"key":"10193_CR15","doi-asserted-by":"crossref","unstructured":"Goyal, R., Kahou, S.E., Michalski, V., Materzynska, J., Westphal, S., Kim, H. & Deutscher, J. (2017). The \"something something\" video database for learning and evaluating visual common sense. Proceedings of the IEEE international conference on computer vision (iccv) (pp. 5843\u20135851)","DOI":"10.1109\/ICCV.2017.622"},{"key":"10193_CR16","doi-asserted-by":"crossref","unstructured":"Grauman, K., et\u00a0al. (2022). Ego4D: Around the world in 3,000 hours of egocentric video. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (cvpr) (pp. 18995\u201319012)","DOI":"10.1109\/CVPR52688.2022.01842"},{"issue":"4","key":"10193_CR17","doi-asserted-by":"publisher","first-page":"2585","DOI":"10.1109\/TRO.2023.3245431","volume":"39","author":"H Guo","year":"2023","unstructured":"Guo, H., Liu, Z., Shi, R., Yau, W. Y., & Rus, D. (2023). Cross-entropy regularized policy gradient for multirobot nonadversarial moving target search. IEEE Transactions on Robotics, 39(4), 2585\u20132603. https:\/\/doi.org\/10.1109\/TRO.2023.3245431","journal-title":"IEEE Transactions on Robotics"},{"key":"10193_CR18","unstructured":"Hafner, D., Lillicrap, T., Norouzi, M. & Ba, J. (2019). Learning latent dynamics for planning from pixels. Proceedings of the 36th international conference on machine learning (icml) (Vol.\u00a097, pp. 2555\u20132565). PMLR"},{"issue":"3","key":"10193_CR19","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1037\/xge0000599","volume":"148","author":"MK Ho","year":"2019","unstructured":"Ho, M. K., Cushman, F., Littman, M. L., & Austerweil, J. L. (2019). People teach with rewards and punishments as communication, not reinforcement. Journal of Experimental Psychology: General, 148(3), 520\u2013549. https:\/\/doi.org\/10.1037\/xge0000599","journal-title":"Journal of Experimental Psychology: General"},{"key":"10193_CR20","unstructured":"Ho, M.K., Littman, M.L., Cushman, F. & Austerweil, J.L. (2015). Teaching with rewards and punishments: Reinforcement or communication? Proceedings of the 37th annual meeting of the cognitive science society (cogsci) (pp. 920\u2013925)"},{"issue":"2","key":"10193_CR21","doi-asserted-by":"publisher","first-page":"1267","DOI":"10.1109\/TRO.2022.3196344","volume":"39","author":"Z Hu","year":"2023","unstructured":"Hu, Z., Zheng, Y., & Pan, J. (2023). Grasping living objects with adversarial behaviors using inverse reinforcement learning. IEEE Transactions on Robotics, 39(2), 1267\u20131282. https:\/\/doi.org\/10.1109\/TRO.2022.3196344","journal-title":"IEEE Transactions on Robotics"},{"key":"10193_CR22","doi-asserted-by":"crossref","unstructured":"Huang, D.A., Nair, P., Xu, D., Zhu, Y., Garg, A., Fei-Fei, L. & Savarese, S. (2019). Neural task graphs: Generalizing to unseen tasks from a single video demonstration. Proceedings of the ieee conference on computer vision and pattern recognition (cvpr) (pp. 8565\u20138574)","DOI":"10.1109\/CVPR.2019.00876"},{"key":"10193_CR23","unstructured":"James, S., Bloesch, M. & Davison, A.J. (2018). Task-embedded control networks for few-shot imitation learning. Proceedings of the 2nd conference on robot learning (corl) (Vol.\u00a087, pp. 783\u2013795). PMLR"},{"key":"10193_CR24","unstructured":"Jang, E., Chebotar, Y., Sermanet, P., Finn, C., Levine, S., Schaal, S. & Khansari, M. (2021). BC-Z: Zero-shot task generalization with robotic imitation learning. Proceedings of the 38th international conference on machine learning (icml) (Vol.\u00a0139, pp. 4703\u20134712). PMLR"},{"issue":"4","key":"10193_CR25","doi-asserted-by":"publisher","first-page":"1382","DOI":"10.1109\/TCDS.2021.3130235","volume":"14","author":"R Jiang","year":"2022","unstructured":"Jiang, R., He, B., Wang, Z., Zhou, Y., Xu, S., & Li, X. (2022). A novel simulation-reality closed-loop learning framework for autonomous robot skill learning. IEEE Transactions on Cognitive and Developmental Systems, 14(4), 1382\u20131393. https:\/\/doi.org\/10.1109\/TCDS.2021.3130235","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"10193_CR26","doi-asserted-by":"crossref","unstructured":"Karnan, H., Warnell, G., Xiao, X. & Stone, P. (2022). VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation. 2022 ieee international conference on robotics and automation (icra) (p.2497-2503)","DOI":"10.1109\/ICRA46639.2022.9812316"},{"key":"10193_CR27","unstructured":"Le\u00a0Paine, T., Shah, S., Hill, M., Durugkar, I., Isbell, C., Stone, P. & Kamat, V. (2018). One-shot high-fidelity imitation: Training large-scale deep nets with rl. (arXiv preprint arXiv:1810.05017)"},{"key":"10193_CR28","unstructured":"Lynch, C., & Sermanet, P. (2020). Grounding language in play. (arXiv preprint arXiv:2005.07648)"},{"key":"10193_CR29","unstructured":"Ma, Y.J., Sodhani, S., Jayaraman, D., Bastani, O., Kumar, V., Zhang, A. (2022). VIP: Towards universal visual reward and representation via value-implicit pre-training. (arXiv preprint arXiv:2210.00030)"},{"key":"10193_CR30","doi-asserted-by":"crossref","unstructured":"Monteiro, J., Gavenski, N., Granada, R., Meneguzzi, F. & Barros, R. (2020). Augmented behavioral cloning from observation. 2020 international joint conference on neural networks (ijcnn) (pp. 1\u20138). IEEE","DOI":"10.1109\/IJCNN48605.2020.9207672"},{"key":"10193_CR31","doi-asserted-by":"crossref","unstructured":"Nagabandi, A., Kahn, G., Fearing, R.S. & Levine, S. (2018). Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. Proceedings of the IEEE international conference on robotics and automation (icra) (pp. 7559\u20137566)","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"10193_CR32","unstructured":"Nair, S., Rajeswaran, A., Kumar, V., Finn, C. & Gupta, A. (2022). R3M: A universal visual representation for robot manipulation. Proceedings of the 6th conference on robot learning (corl). PMLR"},{"key":"10193_CR33","doi-asserted-by":"crossref","unstructured":"Palan, M., Shevchuk, G., Landolfi, N.C. & Sadigh, D. (2019). Learning reward functions by integrating human demonstrations and preferences. Proceedings of robotics: Science and systems (rss)","DOI":"10.15607\/RSS.2019.XV.023"},{"key":"10193_CR34","doi-asserted-by":"crossref","unstructured":"Pathak, D., Gandhi, D. & Gupta, A. (2018). Zero-shot visual imitation. Proceedings of the IEEE conference on computer vision and pattern recognition workshops (cvprw) (pp. 2050\u20132053)","DOI":"10.1109\/CVPRW.2018.00278"},{"key":"10193_CR35","unstructured":"Pinneri, C., Srinivasan, S., Balakrishna, A., Calandra, R., Gandhi, D. & Pathak, D. (2022). Sample-efficient cross-entropy method for real-time planning. Proceedings of the 4th conference on robot learning (corl) (Vol.\u00a0155, pp. 334\u2013345). PMLR"},{"key":"10193_CR36","doi-asserted-by":"crossref","unstructured":"Pirk, S., Khansari, M., Bai, Y., Lynch, C. & Sermanet, P. (2020). Online learning of object representations by appearance space feature alignment. Proceedings of the IEEE international conference on robotics and automation (icra) (pp. 10711\u201310717)","DOI":"10.1109\/ICRA40945.2020.9196567"},{"key":"10193_CR37","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S. & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. Proceedings of the 38th international conference on machine learning (icml)"},{"issue":"2","key":"10193_CR38","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1109\/TCDS.2022.3150261","volume":"15","author":"R Rayyes","year":"2023","unstructured":"Rayyes, R., Donat, H., Steil, J., & Spranger, M. (2023). Interest-driven exploration with observational learning for developmental robots. IEEE Transactions on Cognitive and Developmental Systems, 15(2), 250\u2013262. https:\/\/doi.org\/10.1109\/TCDS.2022.3150261","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"issue":"7","key":"10193_CR39","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1002\/rnc.1043","volume":"16","author":"A Richards","year":"2006","unstructured":"Richards, A., & How, J. P. (2006). Robust variable horizon model predictive control for vehicle maneuvering. International Journal of Robust and Nonlinear Control, 16(7), 333\u2013351. https:\/\/doi.org\/10.1002\/rnc.1043","journal-title":"International Journal of Robust and Nonlinear Control"},{"key":"10193_CR40","unstructured":"Roy, N., Byravan, A., Schneider, J., et\u00a0al. (2021). From machine learning to robotics: Challenges and opportunities for embodied intelligence. (arXiv preprint arXiv:2110.15245)"},{"key":"10193_CR41","doi-asserted-by":"crossref","unstructured":"Scalise, R., Thomason, J., Bisk, Y. & Srinivasa, S. (2019). Improving robot success detection using static object data. Proceedings of the ieee\/rsj international conference on intelligent robots and systems (iros) (pp. 4564\u20134570)","DOI":"10.1109\/IROS40897.2019.8968142"},{"key":"10193_CR42","doi-asserted-by":"crossref","unstructured":"Sermanet, P., Lynch, C., Chebotar, Y., Hsu, J., Jang, E., Schaal, S. & Levine, S. (2018). Time-contrastive networks: Self-supervised learning from video. 2018 ieee international conference on robotics and automation (icra) (p.1134-1141). Brisbane, QLD, Australia","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"10193_CR43","doi-asserted-by":"crossref","unstructured":"Sermanet, P., Lynch, C., Hsu, J. & Levine, S. (2017). Time-contrastive networks: Self-supervised learning from multi-view observation. Proceedings of the IEEE conference on computer vision and pattern recognition workshops (cvprw) (pp. 1134\u20131142)","DOI":"10.1109\/CVPRW.2017.69"},{"key":"10193_CR44","doi-asserted-by":"crossref","unstructured":"Sermanet, P., Xu, K. & Levine, S. (2017). Unsupervised perceptual rewards for imitation learning. (arXiv preprint arXiv:1612.06699)","DOI":"10.15607\/RSS.2017.XIII.050"},{"issue":"12\u201314","key":"10193_CR45","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1177\/02783649211040569","volume":"40","author":"L Shao","year":"2021","unstructured":"Shao, L., Migimatsu, T., Zhang, Q., Yang, K., & Bohg, J. (2021). Concept2robot: Learning manipulation concepts from instructions and human demonstrations. The International Journal of Robotics Research, 40(12\u201314), 1445\u20131461. https:\/\/doi.org\/10.1177\/02783649211040569","journal-title":"The International Journal of Robotics Research"},{"key":"10193_CR46","unstructured":"Stepputtis, S., Campbell, J., Phielipp, M., Lee, S., Baral, C. & Ben\u00a0Amor, H. (2020). Language-conditioned imitation learning for robot manipulation tasks. Advances in neural information processing systems (neurips) (Vol.\u00a033, pp. 13139\u201313151)"},{"issue":"6","key":"10193_CR47","doi-asserted-by":"publisher","first-page":"1313","DOI":"10.1109\/TRO.2017.2750579","volume":"33","author":"J Suh","year":"2017","unstructured":"Suh, J., Gong, J., & Oh, S. (2017). Fast sampling-based cost-aware path planning with nonmyopic extensions using cross entropy. IEEE Transactions on Robotics, 33(6), 1313\u20131326. https:\/\/doi.org\/10.1109\/TRO.2017.2750579","journal-title":"IEEE Transactions on Robotics"},{"issue":"1","key":"10193_CR48","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1109\/TRO.2018.2878318","volume":"35","author":"TG Thuruthel","year":"2019","unstructured":"Thuruthel, T. G., Falotico, E., Renda, F., & Laschi, C. (2019). Model-based reinforcement learning for closed-loop dynamic control of soft robotic manipulators. IEEE Transactions on Robotics, 35(1), 124\u2013134. https:\/\/doi.org\/10.1109\/TRO.2018.2878318","journal-title":"IEEE Transactions on Robotics"},{"key":"10193_CR49","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T. & Tassa, Y. (2012). MuJoCo: A physics engine for model-based control. Proceedings of the IEEE\/RSJ international conference on intelligent robots and systems (iros) (pp. 5026\u20135033)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"10193_CR50","doi-asserted-by":"crossref","unstructured":"Torabi, F., Warnell, G. & Stone, P. (2018). Behavioral cloning from observation. 2018 international joint conferences on artificial intelligence (pp. 4950\u20134957)","DOI":"10.24963\/ijcai.2018\/687"},{"key":"10193_CR51","doi-asserted-by":"crossref","unstructured":"Torabi, F., Warnell, G. & Stone, P. (2019). Imitation learning from video by leveraging proprioception. 2019 international joint conference on artificial intelligence (pp. 3585\u20133591)","DOI":"10.24963\/ijcai.2019\/497"},{"key":"10193_CR52","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N. & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems (neurips) (Vol.\u00a030, pp. 5998\u20136008)"},{"key":"10193_CR53","unstructured":"Wang, T., & Ba, J. (2020). Exploring model-based planning with policy networks. Proceedings of the 8th international conference on learning representations (iclr)"},{"key":"10193_CR54","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1007\/s10514-023-10118-4","volume":"47","author":"T Wang","year":"2023","unstructured":"Wang, T., Dhiman, V., & Atanasov, N. (2023). Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning. Autonomous Robots, 47, 809\u2013830. https:\/\/doi.org\/10.1007\/s10514-023-10118-4","journal-title":"Autonomous Robots"},{"issue":"4","key":"10193_CR55","doi-asserted-by":"publisher","first-page":"1306","DOI":"10.1109\/TCDS.2021.3122037","volume":"14","author":"H Wu","year":"2022","unstructured":"Wu, H., Yan, W., Xu, Z., & Zhou, X. (2022). A framework of improving human demonstration efficiency for goal-directed robot skill learning. IEEE Transactions on Cognitive and Developmental Systems, 14(4), 1306\u20131317. https:\/\/doi.org\/10.1109\/TCDS.2021.3122037","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"10193_CR56","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lian, W., Unhelkar, V., Tomizuka, M. & Schaal, S. (2021). Learning dense rewards for contact-rich manipulation tasks. Proceedings of the ieee international conference on robotics and automation (icra) (pp. 5840\u20135846)","DOI":"10.1109\/ICRA48506.2021.9561891"},{"issue":"4","key":"10193_CR57","doi-asserted-by":"publisher","first-page":"5490","DOI":"10.1109\/LRA.2020.3011107","volume":"5","author":"Z Wu","year":"2020","unstructured":"Wu, Z., Sun, L., Zhan, W., Yang, C., & Tomizuka, M. (2020). Efficient sampling-based maximum entropy inverse reinforcement learning with application to autonomous driving. IEEE Robotics and Automation Letters, 5(4), 5490\u20135497. https:\/\/doi.org\/10.1109\/LRA.2020.3011107","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10193_CR58","doi-asserted-by":"crossref","unstructured":"Xiong, H., Li, Q., Chen, Y- C., Bharadhwaj, H., Sinha, S. & Garg, A. (2021a). Learning by watching: Physical imitation of manipulation skills from human videos. 2021 IEEE\/RSJ international conference on intelligent robots and systems (iros) (p.7827-7834).","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"10193_CR59","doi-asserted-by":"crossref","unstructured":"Xiong, H., Li, Q., Chen, Y.C., Bharadhwaj, H., Sinha, S. & Garg, A. (2021b). Learning by watching: Physical imitation of manipulation skills from human videos. Proceedings of the IEEE\/RSJ international conference on intelligent robots and systems (iros) (pp. 2305\u20132312)","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"10193_CR60","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhang, W., Lu, W., Wang, H. & Li, Y. (2019). Learning actions from human demonstration video for robotic manipulation. 2019 IEEE\/RSJ international conference on intelligent robots and systems (iros) (pp. 1805\u20131811). IEEE","DOI":"10.1109\/IROS40897.2019.8968278"},{"key":"10193_CR61","unstructured":"Young, S., Gandhi, D., Tulsiani, S., Gupta, A., Abbeel, P. & Pinto, L. (2020). Visual imitation made easy. Proceedings of the 3rd conference on robot learning (corl) (Vol.\u00a0100, pp. 1085\u20131097). PMLR"},{"key":"10193_CR62","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K. & Finn, C. (2020). Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning. Proceedings of the 3rd conference on robot learning (corl) (Vol.\u00a0100, pp. 1094\u20131100). PMLR"},{"key":"10193_CR63","doi-asserted-by":"crossref","unstructured":"Yu, T., Quillen, D., He, Z., Julian, R., Hausman, K., Finn, C. & Levine, S. (2018). One-shot imitation from observing humans via domain-adaptive meta-learning. Proceedings of robotics: Science and systems (rss)","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"10193_CR64","unstructured":"Zakka, K., Zeng, A., Florence, P., Tompson, J., Bohg, J. & Dwibedi, D. (2021). XIRL: Cross-embodiment inverse reinforcement learning. Proceedings of the 38th international conference on machine learning (icml) (Vol.\u00a0139, pp. 12356\u201312366). PMLR"},{"key":"10193_CR65","unstructured":"Zhou, A., Xu, Z., Rothfuss, J., Ajay, A., Held, D., Koltun, V. & Abbeel, P. (2020). Watch, try, learn: Meta-learning from demonstrations and rewards. Proceedings of the 8th international conference on learning representations (iclr)"},{"key":"10193_CR66","doi-asserted-by":"crossref","unstructured":"Zhu, J- Y., Park, T., Isola, P. & Efros, A.A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE international conference on computer vision (iccv) (pp. 2223\u20132232)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-025-10193-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10514-025-10193-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-025-10193-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T05:32:01Z","timestamp":1751088721000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10514-025-10193-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,15]]},"references-count":66,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10193"],"URL":"https:\/\/doi.org\/10.1007\/s10514-025-10193-9","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"type":"print","value":"0929-5593"},{"type":"electronic","value":"1573-7527"}],"subject":[],"published":{"date-parts":[[2025,4,15]]},"assertion":[{"value":"28 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2025","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 no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"10"}}