{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T07:11:07Z","timestamp":1768115467596,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819544448","type":"print"},{"value":"9789819544455","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4445-5_25","type":"book-chapter","created":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T03:44:26Z","timestamp":1768103066000},"page":"360-374","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Parameter-Space Policy Composition for\u00a0Sim-to-Real Transfer in\u00a0Quadruped Locomotion Control"],"prefix":"10.1007","author":[{"given":"Yuta","family":"Goto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0712-268X","authenticated-orcid":false,"given":"Satoshi","family":"Yamamori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9572-089X","authenticated-orcid":false,"given":"Satoshi","family":"Yagi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4115-1919","authenticated-orcid":false,"given":"Jun","family":"Morimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"25_CR1","unstructured":"Ahn, M., et al.: ROBEL: RObotics BEnchmarks for learning with low-cost robots. In: The Proceedings of Conference on Robot Learning (2019)"},{"key":"25_CR2","unstructured":"Badia, A.P., et al.: Agent57: outperforming the atari human benchmark. In: Proceedings of International Conference on Machine Learning, vol.\u00a0119, pp. 507\u2013517 (2020)"},{"key":"25_CR3","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1023\/A:1018054314350","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman, L.: Bagging predictors. Mach. Learn. 24, 123\u2013140 (1996)","journal-title":"Mach. Learn."},{"key":"25_CR4","unstructured":"Czarnecki, W.M., Pascanu, R., Osindero, S., Jayakumar, S., Swirszcz, G., Jaderberg, M.: Distilling policy distillation. In: The Proceedings of International Conference on Artificial Intelligence and Statistics, vol. 89, pp. 1331\u20131340 (2019). https:\/\/proceedings.mlr.press\/v89\/czarnecki19a.html"},{"key":"25_CR5","doi-asserted-by":"publisher","unstructured":"Doya, K., Samejima, K., Katagiri, K.I., Kawato, M.: Multiple model-based reinforcement learning. Neural Comput. 14(6), 1347\u20131369 (2002). https:\/\/doi.org\/10.1162\/089976602753712972","DOI":"10.1162\/089976602753712972"},{"key":"25_CR6","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: The Proceedings of International Conference on Machine Learning (2018)"},{"key":"25_CR7","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: Advances in Neural Information Processing Systems: Deep Learning Workshop (2015)"},{"key":"25_CR8","unstructured":"Ilharco, G., et al.: Editing models with task arithmetic. arXiv preprint arXiv:2212.04089 (2022)"},{"issue":"2","key":"25_CR9","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1162\/neco.1994.6.2.181","volume":"6","author":"MI Jordan","year":"1994","unstructured":"Jordan, M.I., Jacobs, R.A.: Hierarchical mixtures of experts and the EM algorithm. Neural Comput. 6(2), 181\u2013214 (1994). https:\/\/doi.org\/10.1162\/neco.1994.6.2.181","journal-title":"Neural Comput."},{"key":"25_CR10","doi-asserted-by":"publisher","unstructured":"Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., Hutter, M.: Learning quadrupedal locomotion over challenging terrain. Sci. Rob. 5(47), eabc5986 (2020). https:\/\/doi.org\/10.1126\/scirobotics.abc5986","DOI":"10.1126\/scirobotics.abc5986"},{"key":"25_CR11","unstructured":"Levine, S.: Reinforcement learning and control as probabilistic inference: tutorial and review. arXiv preprint arXiv:1805.00909 (2018)"},{"key":"25_CR12","doi-asserted-by":"publisher","unstructured":"Miki, T., Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., Hutter, M.: Learning robust perceptive locomotion for quadrupedal robots in the wild. Sci. Rob. 7(62), eabk2822 (2022). https:\/\/doi.org\/10.1126\/scirobotics.abk2822","DOI":"10.1126\/scirobotics.abk2822"},{"key":"25_CR13","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, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"25_CR14","unstructured":"Osband, I., Blundell, C., Pritzel, A., Van\u00a0Roy, B.: Deep exploration via bootstrapped DQN. In: Advances in Neural Information Processing Systems (2016)"},{"key":"25_CR15","unstructured":"Parisotto, E., Ba, J.L., Salakhutdinov, R.: Actor-mimic: deep multitask and transfer reinforcement learning. In: The Proceedings of International Conference on Learning Representations (2015)"},{"key":"25_CR16","doi-asserted-by":"publisher","unstructured":"Peng, X.B., Coumans, E., Zhang, T., Lee, T.W.E., Tan, J., Levine, S.: Learning agile robotic locomotion skills by imitating animals. In: The Proceedings of Robotics: Science and Systems (RSS) (2020). https:\/\/doi.org\/10.15607\/RSS.2020.XVI.064","DOI":"10.15607\/RSS.2020.XVI.064"},{"key":"25_CR17","unstructured":"Ruder, S.: An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017)"},{"key":"25_CR18","unstructured":"Rusu, A.A., et al.: Policy distillation. In: The Proceedings of International Conference on Learning Representations (2015)"},{"key":"25_CR19","unstructured":"Schmitt, S., et\u00a0al.: Kickstarting deep reinforcement learning. In: Advances in Neural Information Processing Systems: Deep Learning Workshop (2018)"},{"key":"25_CR20","unstructured":"Sener, O., Koltun, V.: Multi-task learning as multi-objective optimization. In: Advances in Neural Information Processing Systems (2018)"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","DOI":"10.1038\/nature16961"},{"key":"25_CR22","unstructured":"Sun, L., Zhang, H., Xu, W., Tomizuka, M.: PaCo: parameter-compositional multi-task reinforcement learning. In: Advances in Neural Information Processing Systems (2022)"},{"key":"25_CR23","unstructured":"Teh, Y.W., et al.: Distral: robust multitask reinforcement learning. In: Advances in Neural Information Processing Systems (2017)"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: The Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"issue":"7782","key":"25_CR25","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4445-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T03:44:29Z","timestamp":1768103069000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4445-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819544448","9789819544455"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4445-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"We have no conflicts of interest to declare.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}