{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T10:15:47Z","timestamp":1768817747635,"version":"3.49.0"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031159336","type":"print"},{"value":"9783031159343","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.springer.com\/tdm"},{"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.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-15934-3_32","type":"book-chapter","created":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T00:02:53Z","timestamp":1662422573000},"page":"382-393","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Bi-level Optimization Method for Automatic Reward Shaping of Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Ludi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaolei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghai","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,15]]},"reference":[{"issue":"05","key":"32_CR1","first-page":"888","volume":"15","author":"R Yang","year":"2020","unstructured":"Yang, R., Yan, J., Li, X.: Survey of sparse reward algorithms in reinforcement learning\u2014theory and experiment. CAAI Trans. Intell. Syst. 15(05), 888\u2013899 (2020)","journal-title":"CAAI Trans. Intell. Syst."},{"key":"32_CR2","unstructured":"Ng, A.Y.: Shaping and policy search in reinforcement learning. Ph.D. thesis, University of California, Berkeley (2003)"},{"key":"32_CR3","volume-title":"Reinforcement Learning in Feedback Control\u2014Challenges and Benchmarks from Technical Process Control","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning in Feedback Control\u2014Challenges and Benchmarks from Technical Process Control. MIT Press, Cambridge (1998)"},{"issue":"2","key":"32_CR4","first-page":"226","volume":"56","author":"Y Li","year":"2020","unstructured":"Li, Y., Shao, Z., Zhao, Z., et al.: Design of reward function in deep reinforcement learning for trajectory planning. Comput. Eng. Appl. 56(2), 226\u2013232 (2020)","journal-title":"Comput. Eng. Appl."},{"issue":"C","key":"32_CR5","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.artint.2015.03.009","volume":"225","author":"W Knox","year":"2015","unstructured":"Knox, W., Stone, P.: Framing reinforcement learning from human reward: reward positivity, temporal discounting, episodicity, and performance. Artif. Intell. 225(C), 24\u201350 (2015)","journal-title":"Artif. Intell."},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the 21st International Conference on Machine Learning, Banff, pp. 1\u20138 (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"32_CR7","unstructured":"Ziebart, B.D., Maas, A.L., Bagnell, J.A., et al.: Maximum entropy inverse reinforcement learning. In: Proceedings of the 23rd AAAI Conference on Artificial Intelligence, Illinois, pp. 1433\u20131438 (2008)"},{"key":"32_CR8","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Proceedings of the 30th Conference and Workshop on Neural Information Processing Systems, Barcelona, pp. 4565\u20134573 (2016)"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Wu, Y., Mozifian, M., Shkurti, F.: Shaping rewards for reinforcement learning with imperfect demonstrations using generative models. In: The 2021 International Conference on Robotics and Automation, Xi\u2019an, pp. 6628\u20136634 (2021)","DOI":"10.1109\/ICRA48506.2021.9561333"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., et al.: Curiosity-driven exploration by self-supervised prediction. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Hawaii, pp. 488\u2013489 (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"32_CR11","unstructured":"Jaderberg, M., Czarnecki, W.M., Dunning, I., et al.: Human level performance in first-person multiplayer games with population-based deep reinforcement learning. arXiv (2018)"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Zou, H., Ren, T., Dong, Y., et al.: Learning task-distribution reward shaping with meta-learning. In: The 35th AAAI Conference on Artificial Intelligence, New York (2021)","DOI":"10.1609\/aaai.v35i12.17337"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-15934-3_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T06:17:39Z","timestamp":1663136259000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-15934-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031159336","9783031159343"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-15934-3_32","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":"15 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bristol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"6 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2022\/","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":"561","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":"255","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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}