{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T01:59:07Z","timestamp":1774058347011,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030986810","type":"print"},{"value":"9783030986827","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-030-98682-7_9","type":"book-chapter","created":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T11:04:41Z","timestamp":1647860681000},"page":"103-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Sample Efficiency in\u00a0Behavior Learning by\u00a0Using Sub-optimal Planners for\u00a0Robots"],"prefix":"10.1007","author":[{"given":"Emanuele","family":"Antonioni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Riccio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Nardi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,22]]},"reference":[{"key":"9_CR1","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/978-3-030-27544-0_11","volume-title":"RoboCup 2018: Robot World Cup XXII","author":"O A\u015f\u0131k","year":"2019","unstructured":"A\u015f\u0131k, O., G\u00f6rer, B., Ak\u0131n, H.L.: End-to-end deep imitation learning: robot soccer case study. In: Holz, D., Genter, K., Saad, M., von Stryk, O. (eds.) RoboCup 2018. LNCS (LNAI), vol. 11374, pp. 137\u2013149. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-27544-0_11"},{"key":"9_CR2","unstructured":"Baker, B., et al.: Emergent tool use from multi-agent autocurricula (2019)"},{"key":"9_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-319-62533-1_1","volume-title":"Elements of Robotics","author":"M Ben-Ari","year":"2018","unstructured":"Ben-Ari, M., Mondada, F.: Robots and their applications. In: Elements of Robotics, pp. 1\u201320. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-62533-1_1"},{"key":"9_CR4","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1162\/153244303765208377","volume":"3","author":"RI Brafman","year":"2003","unstructured":"Brafman, R.I., Tennenholtz, M.: R-max - a general polynomial time algorithm for near-optimal reinforcement learning. J. Mach. Learn. Res. 3, 213\u2013231 (2003). https:\/\/doi.org\/10.1162\/153244303765208377","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"9_CR5","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1007\/s13218-015-0356-1","volume":"29","author":"W B\u00f6hmer","year":"2015","unstructured":"B\u00f6hmer, W., Springenberg, J.T., Boedecker, J., Riedmiller, M., Obermayer, K.: Autonomous learning of state representations for control: an emerging field aims to autonomously learn state representations for reinforcement learning agents from their real-world sensor observations. KI - K\u00fcnstliche Intelligenz 29(4), 353\u2013362 (2015). https:\/\/doi.org\/10.1007\/s13218-015-0356-1","journal-title":"KI - K\u00fcnstliche Intelligenz"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Chatzilygeroudis, K., Rama, R., Kaushik, R., Goepp, D., Vassiliades, V., Mouret, J.: Black-box data-efficient policy search for robotics. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 51\u201358 (2017)","DOI":"10.1109\/IROS.2017.8202137"},{"key":"9_CR7","unstructured":"Cheng, C.A., Yan, X., Wagener, N., Boots, B.: Fast policy learning through imitation and reinforcement. arXiv preprint arXiv:1805.10413 (2018)"},{"key":"9_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/3-540-63912-8_83","volume-title":"Recent Advances in AI Planning","author":"G De Giacomo","year":"1997","unstructured":"De Giacomo, G., Iocchi, L., Nardi, D., Rosati, R.: Planning with sensing for a mobile robot. In: Steel, S., Alami, R. (eds.) ECP 1997. LNCS, vol. 1348, pp. 156\u2013168. Springer, Heidelberg (1997). https:\/\/doi.org\/10.1007\/3-540-63912-8_83"},{"key":"9_CR9","unstructured":"Deisenroth, M., Rasmussen, C.E.: PILCO: a model-based and data-efficient approach to policy search. In: Proceedings of the 28th International Conference on machine learning (ICML-11), pp. 465\u2013472 (2011)"},{"issue":"1","key":"9_CR10","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1017\/S0269888915000181","volume":"31","author":"S Devlin","year":"2016","unstructured":"Devlin, S., Kudenko, D.: Plan-based reward shaping for multi-agent reinforcement learning. Knowl. Eng. Rev. 31(1), 44\u201358 (2016). https:\/\/doi.org\/10.1017\/S0269888915000181","journal-title":"Knowl. Eng. Rev."},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"9_CR12","doi-asserted-by":"publisher","unstructured":"Ingrand, F., Ghallab, M.: Deliberation for autonomous robots: a survey. Artif. Intell. 247, 10\u201344 (2017). https:\/\/doi.org\/10.1016\/j.artint.2014.11.003. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0004370214001350. Special Issue on AI and Robotics","DOI":"10.1016\/j.artint.2014.11.003"},{"key":"9_CR13","unstructured":"Iocchi, L., Nardi, D., Rosati, R.: Generation of strong cyclic plans with incomplete information and sensing 2(4), 58\u201365 (2005)"},{"key":"9_CR14","unstructured":"Jiang, Y., Yang, F., Zhang, S., Stone, P.: Integrating task-motion planning with reinforcement learning for robust decision making in mobile robots. ArXiv abs\/1811.08955 (2018)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Johannink, T., et al.: Residual reinforcement learning for robot control. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 6023\u20136029. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"9_CR16","series-title":"Springer Tracts in Advanced Robotics","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/978-3-319-03194-1_2","volume-title":"Learning Motor Skills","author":"J Kober","year":"2014","unstructured":"Kober, J., Peters, J.: Reinforcement learning in robotics: a survey. In: Learning Motor Skills. STAR, vol. 97, pp. 9\u201367. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-03194-1_2"},{"key":"9_CR17","unstructured":"Kurenkov, A., Mandlekar, A., Martin-Martin, R., Savarese, S., Garg, A.: AC-Teach: a Bayesian actor-critic method for policy learning with an ensemble of suboptimal teachers. arXiv preprint arXiv:1909.04121 (2019)"},{"key":"9_CR18","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.artint.2016.07.004","volume":"241","author":"M Leonetti","year":"2016","unstructured":"Leonetti, M., Iocchi, L., Stone, P.: A synthesis of automated planning and reinforcement learning for efficient, robust decision-making. Artif. Intell. 241, 103\u2013130 (2016). https:\/\/doi.org\/10.1016\/j.artint.2016.07.004","journal-title":"Artif. Intell."},{"key":"9_CR19","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1007\/978-3-319-29339-4_24","volume-title":"RoboCup 2015: Robot World Cup XIX","author":"DL Leottau","year":"2015","unstructured":"Leottau, D.L., Ruiz-del-Solar, J., MacAlpine, P., Stone, P.: A study of layered learning strategies applied to individual behaviors in robot soccer. In: Almeida, L., Ji, J., Steinbauer, G., Luke, S. (eds.) RoboCup 2015. LNCS (LNAI), vol. 9513, pp. 290\u2013302. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-29339-4_24"},{"key":"9_CR20","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/978-3-319-68792-6_16","volume-title":"RoboCup 2016: Robot World Cup XX","author":"H Mellmann","year":"2017","unstructured":"Mellmann, H., Schlotter, B., Blum, C.: Simulation based selection of actions for a humanoid soccer-robot. In: Behnke, S., Sheh, R., Sar\u0131el, S., Lee, D.D. (eds.) RoboCup 2016. LNCS (LNAI), vol. 9776, pp. 193\u2013205. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-68792-6_16"},{"key":"9_CR21","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"9_CR22","doi-asserted-by":"publisher","unstructured":"Mohanan, M., Salgoankar, A.: A survey of robotic motion planning in dynamic environments. Robot. Auton. Syst. 100, 171\u2013185 (2018). https:\/\/doi.org\/10.1016\/j.robot.2017.10.011. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0921889017300313","DOI":"10.1016\/j.robot.2017.10.011"},{"key":"9_CR23","doi-asserted-by":"publisher","unstructured":"Noda, K., Arie, H., Suga, Y., Ogata, T.: Multimodal integration learning of robot behavior using deep neural networks. Robot. Auton. Syst. 62(6), 721\u2013736 (2014). https:\/\/doi.org\/10.1016\/j.robot.2014.03.003. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0921889014000396","DOI":"10.1016\/j.robot.2014.03.003"},{"key":"9_CR24","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/3-540-45329-6_38","volume-title":"Progress in Artificial Intelligence","author":"E Onaindia","year":"2001","unstructured":"Onaindia, E., Sapena, O., Sebastia, L., Marzal, E.: SimPlanner: an execution-monitoring system for replanning in dynamic worlds. In: Brazdil, P., Jorge, A. (eds.) EPIA 2001. LNCS (LNAI), vol. 2258, pp. 393\u2013400. Springer, Heidelberg (2001). https:\/\/doi.org\/10.1007\/3-540-45329-6_38"},{"key":"9_CR25","unstructured":"Pierson, H.A., Gashler, M.S.: Deep learning in robotics: a review of recent research. CoRR abs\/1707.07217 (2017). http:\/\/arxiv.org\/abs\/1707.07217"},{"key":"9_CR26","doi-asserted-by":"publisher","unstructured":"Polydoros, A., Nalpantidis, L., Kr\u00fcger, V.: Real-time deep learning of robotic manipulator inverse dynamics (2015). https:\/\/doi.org\/10.1109\/IROS.2015.7353857","DOI":"10.1109\/IROS.2015.7353857"},{"issue":"6","key":"9_CR27","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/S1364-6613(99)01327-3","volume":"3","author":"S Schaal","year":"1999","unstructured":"Schaal, S.: Is imitation learning the route to humanoid robots? Trends Cogn. Sci. 3(6), 233\u2013242 (1999)","journal-title":"Trends Cogn. Sci."},{"key":"9_CR28","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"9_CR29","unstructured":"Watter, M., Springenberg, J.T., Boedecker, J., Riedmiller, M.A.: Embed to control: a locally linear latent dynamics model for control from raw images. CoRR abs\/1506.07365 (2015). http:\/\/arxiv.org\/abs\/1506.07365"}],"container-title":["Lecture Notes in Computer Science","RoboCup 2021: Robot World Cup XXIV"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-98682-7_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T01:01:58Z","timestamp":1774054918000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-98682-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030986810","9783030986827"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-98682-7_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 March 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RoboCup","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Robot World Cup","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"robocup2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.robocup.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"42","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"19","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The volume also contains 10 reviewed champion papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}