{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:37:00Z","timestamp":1743151020214,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031377419"},{"type":"electronic","value":"9783031377426"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-37742-6_52","type":"book-chapter","created":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T06:02:51Z","timestamp":1690869771000},"page":"674-686","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Intuitive Physics Guided Exploration for\u00a0Sample Efficient Sim2real Transfer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2792-492X","authenticated-orcid":false,"given":"Buddhika Laknath","family":"Semage","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8918-3314","authenticated-orcid":false,"given":"Thommen George","family":"Karimpanal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2247-850X","authenticated-orcid":false,"given":"Santu","family":"Rana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8675-6631","authenticated-orcid":false,"given":"Svetha","family":"Venkatesh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,2]]},"reference":[{"key":"52_CR1","unstructured":"Pymunk. http:\/\/www.pymunk.org\/"},{"key":"52_CR2","unstructured":"Akkaya, I., et al.: Solving rubik\u2019s cube with a robot hand. arXiv preprint arXiv:1910.07113 (2019)"},{"issue":"47","key":"52_CR3","doi-asserted-by":"publisher","first-page":"29302","DOI":"10.1073\/pnas.1912341117","volume":"117","author":"KR Allen","year":"2020","unstructured":"Allen, K.R., Smith, K.A., Tenenbaum, J.B.: Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning. Proc. Natl. Acad. Sci. 117(47), 29302\u201329310 (2020)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"52_CR4","doi-asserted-by":"crossref","unstructured":"Allevato, A., Short, E.S., Pryor, M., Thomaz, A.: Tunenet: one-shot residual tuning for system identification and sim-to-real robot task transfer. In: Conference on Robot Learning, pp. 445\u2013455. PMLR (2020)","DOI":"10.1007\/s10514-020-09925-w"},{"key":"52_CR5","unstructured":"Bakhtin, A., van der Maaten, L., Johnson, J., Gustafson, L., Girshick, R.: PHYRE: a new benchmark for physical reasoning. In: NeurIPS, pp. 5082\u20135093 (2019)"},{"key":"52_CR6","unstructured":"Carr, T., Chli, M., Vogiatzis, G.: Domain adaptation for reinforcement learning on the atari. In: AAMAS 2019, Richland, SC, pp. 1859\u20131861 (2019)"},{"issue":"1","key":"52_CR7","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"PT De Boer","year":"2005","unstructured":"De Boer, P.T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross-entropy method. Ann. Oper. Res. 134(1), 19\u201367 (2005)","journal-title":"Ann. Oper. Res."},{"key":"52_CR8","unstructured":"Denil, M., Agrawal, P., Kulkarni, T.D., Erez, T., Battaglia, P.W., de Freitas, N.: Learning to perform physics experiments via deep reinforcement learning. In: ICLR. OpenReview.net (2017)"},{"key":"52_CR9","doi-asserted-by":"publisher","unstructured":"Desai, S., Karnan, H., Hanna, J.P., Warnell, G., a. P. Stone: stochastic grounded action transformation for robot learning in simulation. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6106\u20136111 (2020). https:\/\/doi.org\/10.1109\/IROS45743.2020.9340780","DOI":"10.1109\/IROS45743.2020.9340780"},{"key":"52_CR10","doi-asserted-by":"crossref","unstructured":"Du, Y., Watkins, O., Darrell, T., Abbeel, P., Pathak, D.: Auto-tuned sim-to-real transfer. arXiv preprint arXiv:2104.07662 (2021)","DOI":"10.1109\/ICRA48506.2021.9562091"},{"key":"52_CR11","unstructured":"Dubey, R., Agrawal, P., Pathak, D., Griffiths, T.L., Efros, A.A.: Investigating human priors for playing video games. arXiv preprint arXiv:1802.10217 (2018)"},{"key":"52_CR12","unstructured":"Farchy, A., Barrett, S., MacAlpine, P., Stone, P.: Humanoid robots learning to walk faster: from the real world to simulation and back. In: AAMAS, pp. 39\u201346 (2013)"},{"key":"52_CR13","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez, F., Veloso, M.: Probabilistic policy reuse in a reinforcement learning agent. In: AAMAS, pp. 720\u2013727 (2006)","DOI":"10.1145\/1160633.1160762"},{"key":"52_CR14","unstructured":"Fragkiadaki, K., Agrawal, P., Levine, S., Malik, J.: Learning visual predictive models of physics for playing billiards. In: Bengio, Y., LeCun, Y. (eds.) ICLR 2016, San Juan, Puerto Rico, 2\u20134 May 2016 (2016)"},{"key":"52_CR15","unstructured":"Freeman, D., Ha, D., Metz, L.S.: Learning to predict without looking ahead: world models without forward prediction (2019)"},{"key":"52_CR16","doi-asserted-by":"crossref","unstructured":"Grzeszczuk, R., Terzopoulos, D., Hinton, G.: NeuroAnimator: fast neural network emulation and control of physics-based models. In: SIGGRAPH 1998, pp. 9\u201320. Association for Computing Machinery, New York (1998)","DOI":"10.1145\/280814.280816"},{"key":"52_CR17","doi-asserted-by":"crossref","unstructured":"Hanna, J.P., Stone, P.: Grounded action transformation for robot learning in simulation. In: AAAI, pp. 4931\u20134932. AAAI Press (2017)","DOI":"10.1609\/aaai.v31i1.11124"},{"key":"52_CR18","unstructured":"Janner, M., Levine, S., Freeman, W.T., Tenenbaum, J.B., Finn, C., Wu, J.: Reasoning about physical interactions with Object-Oriented prediction and planning (2018)"},{"key":"52_CR19","unstructured":"Lake, B.M., Baroni, M.: Generalization without systematicity: on the compositional skills of sequence-to-sequence recurrent networks. In: Dy, J.G., Krause, A. (eds.) ICML, Proceedings of Machine Learning Research, vol. 80, pp. 2879\u20132888. PMLR (2018)"},{"key":"52_CR20","doi-asserted-by":"crossref","unstructured":"Li, L., Chu, W., Langford, J., Schapire, R.E.: A contextual-bandit approach to personalized news article recommendation. In: Proceedings of the 19th International Conference on World Wide Web, pp. 661\u2013670 (2010)","DOI":"10.1145\/1772690.1772758"},{"key":"52_CR21","doi-asserted-by":"crossref","unstructured":"Loula, J., Baroni, M., Lake, B.: Rearranging the familiar: testing compositional generalization in recurrent networks. In: Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 108\u2013114 (2018)","DOI":"10.18653\/v1\/W18-5413"},{"issue":"7540","key":"52_CR22","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"2","key":"52_CR23","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1109\/LRA.2021.3052391","volume":"6","author":"F Muratore","year":"2021","unstructured":"Muratore, F., Eilers, C., Gienger, M., Peters, J.: Data-efficient domain randomization with bayesian optimization. IEEE Rob. Autom. Lett. 6(2), 911\u2013918 (2021). https:\/\/doi.org\/10.1109\/LRA.2021.3052391","journal-title":"IEEE Rob. Autom. Lett."},{"key":"52_CR24","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: Proceedings of the 34th ICML, ICML 2017, vol. 70, pp. 2778\u20132787. JMLR.org (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"52_CR25","doi-asserted-by":"crossref","unstructured":"Sadeghi, F., Levine, S.: CAD2RL: real single-image flight without a single real image. In: Amato, N.M., Srinivasa, S.S., Ayanian, N., Kuindersma, S. (eds.) Robotics: Science and Systems XIII, MIT, USA, 2017 (2017)","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"52_CR26","doi-asserted-by":"publisher","unstructured":"Sheckells, M., Garimella, G., Mishra, S., Kobilarov, M.: Using data-driven domain randomization to transfer robust control policies to mobile robots. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 3224\u20133230 (2019). https:\/\/doi.org\/10.1109\/ICRA.2019.8794343","DOI":"10.1109\/ICRA.2019.8794343"},{"key":"52_CR27","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10, 1633\u20131685 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"52_CR28","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 23\u201330 (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"52_CR29","unstructured":"Tsividis, P.A., Pouncy, T., Xu, J.L., Tenenbaum, J.B., Gershman, S.J.: Human learning in atari. In: 2017 AAAI Spring Symposium Series (2017)"},{"key":"52_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, pp. 6000\u20136010. Curran Associates Inc., Red Hook (2017)"},{"key":"52_CR31","unstructured":"Wu, J., Yildirim, I., Lim, J.J., Freeman, B., Tenenbaum, J.: Galileo: perceiving physical object properties by integrating a physics engine with deep learning. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28, pp. 127\u2013135. Curran Associates, Inc. (2015)"},{"key":"52_CR32","doi-asserted-by":"publisher","unstructured":"Xu, Z., Wu, J., Zeng, A., Tenenbaum, J.B., Song, S.: Densephysnet: learning dense physical object representations via multi-step dynamic interactions. In: Bicchi, A., Kress-Gazit, H., Hutchinson, S. (eds.) Robotics: Science and Systems XV, University of Freiburg, Freiburg im Breisgau, Germany, 22\u201326 June 2019 (2019). https:\/\/doi.org\/10.15607\/RSS.2019.XV.046","DOI":"10.15607\/RSS.2019.XV.046"},{"issue":"4","key":"52_CR33","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1109\/TRO.2020.2988642","volume":"36","author":"A Zeng","year":"2020","unstructured":"Zeng, A., Song, S., Lee, J., Rodriguez, A., Funkhouser, T.: Tossingbot: learning to throw arbitrary objects with residual physics. IEEE Trans. Rob. 36(4), 1307\u20131319 (2020). https:\/\/doi.org\/10.1109\/TRO.2020.2988642","journal-title":"IEEE Trans. Rob."},{"key":"52_CR34","unstructured":"Zheng, D., Luo, V., Wu, J., Tenenbaum, J.B.: Unsupervised learning of latent physical properties using Perception-Prediction networks. In: Globerson, A., Silva, R. (eds.) Proceedings of the Thirty-Fourth UAI 2018, Monterey, California, USA, 6\u201310 August 2018, pp. 497\u2013507. AUAI Press (2018)"},{"key":"52_CR35","unstructured":"Zhou, W., Pinto, L., Gupta, A.: Environment probing interaction policies. In: International Conference on Learning Representations (2018)"},{"key":"52_CR36","unstructured":"Zhu, Z., Lin, K., Zhou, J.: Transfer learning in deep reinforcement learning: a survey. arXiv preprint arXiv:2009.07888 (2020)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition, Computer Vision, and Image Processing. ICPR 2022 International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-37742-6_52","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T06:09:09Z","timestamp":1690870149000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-37742-6_52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031377419","9783031377426"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-37742-6_52","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Montr\u00e9al, QC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icpr2022","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}