{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T11:39:48Z","timestamp":1763811588040,"version":"3.40.5"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T00:00:00Z","timestamp":1737590400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T00:00:00Z","timestamp":1737590400000},"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":["Artif Life Robotics"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s10015-025-01003-7","type":"journal-article","created":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T03:54:04Z","timestamp":1737604444000},"page":"245-251","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["An empirical evaluation of a hierarchical reinforcement learning method towards modular robot control"],"prefix":"10.1007","volume":"30","author":[{"given":"Sho","family":"Takeda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Yamamori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Yagi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Morimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,23]]},"reference":[{"key":"1003_CR1","doi-asserted-by":"crossref","unstructured":"Brohan A, Brown N, Carbajal J, Chebotar Y, Dabis J, et al (2023) RT-1: Robotics transformer for real-world control at scale. Proceedings of Robotics: Science and Systems.","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"1003_CR2","doi-asserted-by":"crossref","unstructured":"Gu S, Holly E, Lillicrap T, Levine S (2017) Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. 2017 IEEE International Conference on Robotics and Automation (ICRA). pp. 3389\u20133396","DOI":"10.1109\/ICRA.2017.7989385"},{"issue":"1\u20132","key":"1003_CR3","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton RS, Precup D, Singh S (1999) Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif Intell 112(1\u20132):181\u2013211","journal-title":"Artif Intell"},{"issue":"1","key":"1003_CR4","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/S0921-8890(01)00113-0","volume":"36","author":"J Morimoto","year":"2001","unstructured":"Morimoto J, Doya K (2001) Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning. Robot Auton Syst 36(1):37\u201351","journal-title":"Robot Auton Syst"},{"key":"1003_CR5","unstructured":"Frans K, Ho J, Chen X, Abbeel P, Schulman J (2018) Meta learning shared hierarchies."},{"key":"1003_CR6","unstructured":"Nachum O, Gu S, Lee H, Levine S (2018) Data-Efficient Hierarchical Reinforcement Learning. Advances in Neural Information Processing Systems."},{"key":"1003_CR7","unstructured":"Osa T, Tangkaratt V, Sugiyama M (2018) Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization."},{"key":"1003_CR8","unstructured":"Haarnoja T, Hartikainen K, Abbeel P, Levine S (2018) Latent space policies for hierarchical reinforcement learning. International Conference on Machine Learning pp. 1851\u20131860"},{"issue":"4","key":"1003_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530110","volume":"41","author":"XB Peng","year":"2022","unstructured":"Peng XB, Guo Y, Halper L, Levine S, Fidler S (2022) ASE: large-scale reusable adversarial skill embeddings for physically simulated characters. ACM Trans Graphics (TOG) 41(4):1\u201317","journal-title":"ACM Trans Graphics (TOG)"},{"key":"1003_CR10","unstructured":"Peng XB, Chang M, Zhang G, Abbeel P, Levine S (2019) MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies. Advances in Neural Information Processing Systems 32"},{"issue":"2","key":"1003_CR11","doi-asserted-by":"publisher","first-page":"3623","DOI":"10.1109\/LRA.2021.3060403","volume":"6","author":"S Christen","year":"2021","unstructured":"Christen S, Jendele L, Aksan E, Hilliges O (2021) Learning functionally decomposed hierarchies for continuous control tasks with path planning. IEEE Robot Automat Lett 6(2):3623\u20133630","journal-title":"IEEE Robot Automat Lett"},{"key":"1003_CR12","doi-asserted-by":"crossref","unstructured":"Liu S, Lever G, Wang Z, Merel J, Eslami SMA, et al (2022) From motor control to team play in simulated humanoid football. Sci Robot. 7(69)","DOI":"10.1126\/scirobotics.abo0235"},{"key":"1003_CR13","unstructured":"Jaderberg M, Dalibard V, Osindero S, Czarnecki WM, Donahue J, et al (2017) Population based training of neural networks. arXiv preprint arXiv:1711.09846. Accessed 20 Dec 2023"},{"key":"1003_CR14","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S (2018) Soft actor-critic: Off-Policy Maximum entropy deep reinforcement learning with a stochastic actor. International Conference on Machine Learning pp. 1861\u20131870"},{"key":"1003_CR15","unstructured":"Haarnoja T, Zhou A, Hartikainen K, Tucker G, Ha S, et al (2018) Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905. Accessed 20 Dec 2023"},{"key":"1003_CR16","doi-asserted-by":"crossref","unstructured":"Todorov E, Erez T, Tassa Y (2012) Mujoco: A physics engine for model-based control. 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems pp. 5026\u20135033","DOI":"10.1109\/IROS.2012.6386109"},{"key":"1003_CR17","unstructured":"Zakka K, Tassa Y, MuJoCo Menagerie Contributors (2023) MuJoCo Menagerie: A collection of high-quality simulation models for MuJoCo. https:\/\/github.com\/google-deepmind\/mujoco_menagerie. Accessed 20 Dec 2023"},{"key":"1003_CR18","unstructured":"Franceschetti A (2023) Universal Robots UR5 + Robotiq S Model 3 Finger Gripper. https:\/\/roboti.us\/forum\/index.php?resources\/universal-robots-ur5-robotiq-s-model-3-finger-gripper.22\/. Accessed 20 Dec 2023"},{"key":"1003_CR19","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.inffus.2019.12.004","volume":"58","author":"T Lesort","year":"2020","unstructured":"Lesort T, Lomonaco V, Stoian A, Maltoni D, Filliat D et al (2020) Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges. Information Fusion 58:52\u201368","journal-title":"Information Fusion"},{"key":"1003_CR20","doi-asserted-by":"publisher","first-page":"104427","DOI":"10.1016\/j.robot.2023.104427","volume":"165","author":"S Auddy","year":"2023","unstructured":"Auddy S, Hollenstein J, Saveriano M, Rodr\u00edguez-S\u00e1nchez A, Piater J (2023) Continual learning from demonstration of robotics skills. Robot Auton Syst 165:104427","journal-title":"Robot Auton Syst"}],"container-title":["Artificial Life and Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-025-01003-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10015-025-01003-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-025-01003-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T19:38:22Z","timestamp":1746733102000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10015-025-01003-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,23]]},"references-count":20,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["1003"],"URL":"https:\/\/doi.org\/10.1007\/s10015-025-01003-7","relation":{},"ISSN":["1433-5298","1614-7456"],"issn-type":[{"type":"print","value":"1433-5298"},{"type":"electronic","value":"1614-7456"}],"subject":[],"published":{"date-parts":[[2025,1,23]]},"assertion":[{"value":"30 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}