{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:35:44Z","timestamp":1742974544016,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":14,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819757787"},{"type":"electronic","value":"9789819757794"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-5779-4_19","type":"book-chapter","created":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T07:17:09Z","timestamp":1736493429000},"page":"291-300","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Shapley-Optimized Reinforcement Learning for Human-Machine Collaboration Policy"],"prefix":"10.1007","author":[{"given":"Jie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqun","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongjun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,11]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Baxter, J., Bartlett, P.L.: Infinite-horizon policy-gradient estimation. journal of artificial intelligence research 15, 319\u2013350 (2001)","DOI":"10.1613\/jair.806"},{"key":"19_CR2","doi-asserted-by":"publisher","unstructured":"Harutyunyan, A., Devlin, S., Vrancx, P., Nowe, A.: Expressing arbitrary reward functions as potential-based advice. Proceedings of the AAAI Conference on Artificial Intelligence 29(1) (Feb 2015). https:\/\/doi.org\/10.1609\/aaai.v29i1.9628, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/9628","DOI":"10.1609\/aaai.v29i1.9628"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Heuillet, A., Couthouis, F., D\u00edaz-Rodr\u00edguez, N.: Collective explainable ai: Explaining cooperative strategies and agent contribution in multiagent reinforcement learning with shapley values. IEEE Computational Intelligence Magazine 17(1), 59\u201371 (2022)","DOI":"10.1109\/MCI.2021.3129959"},{"key":"19_CR4","unstructured":"Hu, Y., Wang, W., Jia, H., Wang, Y., Chen, Y., Hao, J., Wu, F., Fan, C.: Learning to utilize shaping rewards: A new approach of reward shaping. Advances in Neural Information Processing Systems 33, 15931\u201315941 (2020)"},{"key":"19_CR5","unstructured":"Hu, Y., Wang, W., Jia, H., Wang, Y., Chen, Y., Hao, J., Wu, F., Fan, C.: Learning to utilize shaping rewards: A new approach of reward shaping (2020)"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Jain, A., Patil, G., Jain, A., Khetarpal, K., Precup, D.: Variance penalized on-policy and off-policy actor-critic. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a035, pp. 7899\u20137907 (2021)","DOI":"10.1609\/aaai.v35i9.16964"},{"key":"19_CR7","unstructured":"Khalid, A., Kirisci, P., Ghrairi, Z., Thoben, K., Pannek, J.: Towards implementing safety and security concepts for human-robot collaboration in the context of industry 4.0. In: 39th International MATADOR Conference on Advanced Manufacturing. vol.\u00a02, pp. 55\u201363 (2017)"},{"key":"19_CR8","unstructured":"Kuba, J.G., Chen, R., Wen, M., Wen, Y., Sun, F., Wang, J., Yang, Y.: Trust region policy optimisation in multi-agent reinforcement learning (2022)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Marwala, T.: Human vs machine rationality, pp. 173\u2013191 (01 2021). 10.1016\/B978-0-12-820676-8.00003-X","DOI":"10.1016\/B978-0-12-820676-8.00003-X"},{"key":"19_CR10","unstructured":"Nguyen, Q.P., Low, B.K.H., Jaillet, P.: Trade-off between payoff and model rewards in shapley-fair collaborative machine learning. Advances in Neural Information Processing Systems 35, 30542\u201330553 (2022)"},{"key":"19_CR11","unstructured":"Precup, D., Sutton, R.S., Singh, S.P.: Eligibility traces for off-policy policy evaluation. In: Proceedings of the Seventeenth International Conference on Machine Learning. p. 759-766. Morgan Kaufmann Publishers Inc. (2000)"},{"issue":"4","key":"19_CR12","doi-asserted-by":"publisher","first-page":"6169","DOI":"10.1109\/LRA.2020.3011353","volume":"5","author":"A Sasagawa","year":"2020","unstructured":"Sasagawa, A., Fujimoto, K., Sakaino, S., Tsuji, T.: Imitation learning based on bilateral control for human-robot cooperation. IEEE Robotics and Automation Letters 5(4), 6169\u20136176 (2020)","journal-title":"IEEE Robotics and Automation Letters"},{"key":"19_CR13","first-page":"13139","volume":"33","author":"S Stepputtis","year":"2020","unstructured":"Stepputtis, S., Campbell, J., Phielipp, M., Lee, S., Baral, C., Ben Amor, H.: Language-conditioned imitation learning for robot manipulation tasks. Adv. Neural. Inf. Process. Syst. 33, 13139\u201313150 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR14","unstructured":"Tessler, C., Mankowitz, D.J., Mannor, S.: Reward constrained policy optimization (2018)"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5779-4_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T08:08:30Z","timestamp":1736496510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5779-4_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819757787","9789819757794"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5779-4_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"11 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gifu","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2024a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dasfaa2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}