{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T13:45:33Z","timestamp":1726062333121},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030367176"},{"type":"electronic","value":"9783030367183"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-36718-3_10","type":"book-chapter","created":{"date-parts":[[2019,12,10]],"date-time":"2019-12-10T08:03:52Z","timestamp":1575965032000},"page":"115-126","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Transferable Policies with Improved Graph Neural Networks on Serial Robotic Structure"],"prefix":"10.1007","author":[{"given":"Fengyi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangzhou","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,12,9]]},"reference":[{"key":"10_CR1","unstructured":"Ammar, H.B., Eaton, E., Ruvolo, P., Taylor, M.: Unsupervised cross-domain transfer for policy gradient reinforcement learning via manifold alignment. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)"},{"key":"10_CR2","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-642-28499-1_2","volume-title":"Adaptive and Learning Agents","author":"HB Ammar","year":"2012","unstructured":"Ammar, H.B., Taylor, M.E.: Reinforcement learning transfer via common subspaces. In: Vrancx, P., Knudson, M., Grze\u015b, M. (eds.) ALA 2011. LNCS (LNAI), vol. 7113, pp. 21\u201336. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-28499-1_2"},{"key":"10_CR3","volume-title":"Network Science","author":"AL Barab\u00e1si","year":"2016","unstructured":"Barab\u00e1si, A.L., et al.: Network Science. Cambridge University Press, Cambridge (2016)"},{"key":"10_CR4","unstructured":"Battaglia, P.W., et al.: Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018)"},{"key":"10_CR5","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"10_CR6","unstructured":"Chang, M.B., Ullman, T., Torralba, A., Tenenbaum, J.B.: A compositional object-based approach to learning physical dynamics. arXiv preprint arXiv:1612.00341 (2016)"},{"key":"10_CR7","series-title":"Springer Proceedings in Advanced Robotics","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-50115-4_1","volume-title":"2016 International Symposium on Experimental Robotics","author":"S Daftry","year":"2017","unstructured":"Daftry, S., Bagnell, J.A., Hebert, M.: Learning transferable policies for monocular reactive MAV control. In: Kuli\u0107, D., Nakamura, Y., Khatib, O., Venture, G. (eds.) ISER 2016. SPAR, vol. 1, pp. 3\u201311. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-50115-4_1"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Devin, C., Gupta, A., Darrell, T., Abbeel, P., Levine, S.: Learning modular neural network policies for multi-task and multi-robot transfer. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2169\u20132176. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989250"},{"issue":"1","key":"10_CR9","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"S Franco","year":"2009","unstructured":"Franco, S., Marco, G., Ah Chung, T., Markus, H., Gabriele, M.: The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61 (2009)","journal-title":"IEEE Trans. Neural Netw."},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: IEEE International Conference on Robotics and Automation (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"10_CR11","unstructured":"Gupta, A., Devin, C., Liu, Y., Abbeel, P., Levine, S.: Learning invariant feature spaces to transfer skills with reinforcement learning. arXiv preprint arXiv:1703.02949 (2017)"},{"key":"10_CR12","unstructured":"Hamrick, J.B., et al.: Relational inductive bias for physical construction in humans and machines. arXiv preprint arXiv:1806.01203 (2018)"},{"key":"10_CR13","unstructured":"Hamrick, J.B., Ballard, A.J., Pascanu, R., Vinyals, O., Heess, N., Battaglia, P.W.: Metacontrol for adaptive imagination-based optimization. arXiv preprint arXiv:1705.02670 (2017)"},{"key":"10_CR14","unstructured":"Hoshen, Y.: VAIN: attentional multi-agent predictive modeling. In: Advances in Neural Information Processing Systems, pp. 2701\u20132711 (2017)"},{"key":"10_CR15","unstructured":"Kipf, T., Fetaya, E., Wang, K.C., Welling, M., Zemel, R.: Neural relational inference for interacting systems. arXiv preprint arXiv:1802.04687 (2018)"},{"issue":"1","key":"10_CR16","first-page":"1334","volume":"17","author":"S Levine","year":"2015","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(1), 1334\u20131373 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR17","unstructured":"Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.: Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 (2015)"},{"key":"10_CR18","unstructured":"Metz, L., Ibarz, J., Jaitly, N., Davidson, J.: Discrete sequential prediction of continuous actions for deep RL. arXiv preprint arXiv:1705.05035 (2017)"},{"key":"10_CR19","unstructured":"Rusu, A.A., et al.: Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)"},{"key":"10_CR20","unstructured":"Sanchez-Gonzalez, A., et al.: Graph networks as learnable physics engines for inference and control. arXiv preprint arXiv:1806.01242 (2018)"},{"issue":"1","key":"10_CR21","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/TNN.2008.2005141","volume":"20","author":"F Scarselli","year":"2008","unstructured":"Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: Computational capabilities of graph neural networks. IEEE Trans. Neural Netw. 20(1), 81\u2013102 (2008)","journal-title":"IEEE Trans. Neural Netw."},{"key":"10_CR22","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"10","key":"10_CR23","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(10), 1633\u20131685 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Toyer, S., Trevizan, F., Thi\u00e9baux, S., Xie, L.: Action schema networks: generalised policies with deep learning. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12089"},{"key":"10_CR26","unstructured":"Wang, T., Liao, R., Ba, J., Fidler, S.: NerveNet: learning structured policy with graph neural networks (2018)"},{"issue":"5","key":"10_CR27","first-page":"709","volume":"17","author":"M Wilson","year":"2006","unstructured":"Wilson, M., Spong, M.W.: Robot modeling and control. Ind. Robot Int. J. 17(5), 709\u2013737 (2006)","journal-title":"Ind. Robot Int. J."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36718-3_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T02:05:46Z","timestamp":1665194746000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-36718-3_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030367176","9783030367183"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36718-3_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ajiips.com.au\/iconip2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}